python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' -a 4741 -l 30 ' -s datou_current_4741 -M 0 -S 0 -U 95,95,120 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 2339854 load datou : 4741 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) load thcls load THCL from format json or kwargs add thcl : 3453 in CacheModelConfig load THCL from format json or kwargs add thcl : 3783 in CacheModelConfig load pdts add pdt : 5732 in CacheModelConfig add pdt : 5972 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4741, datou_cur_ids : ['2710271'] with mtr_portfolio_ids : ['21920562'] and first list_photo_ids : [] new path : /proc/2339854/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, mask_detect, blur_detection, brightness, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 8 ; length of list_pids : 8 ; length of list_args : 8 time to download the photos : 2.253141403198242 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Tue Apr 1 02:01:34 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-04-01 02:01:38.047420: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-04-01 02:01:38.083324: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-04-01 02:01:38.085534: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3e70000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-04-01 02:01:38.085571: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-04-01 02:01:38.089435: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-04-01 02:01:38.502769: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2caf5a70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-04-01 02:01:38.502824: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-04-01 02:01:38.504320: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:01:38.504718: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:01:38.506995: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:01:38.509540: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:01:38.509975: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:01:38.512469: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:01:38.513864: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:01:38.519523: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:01:38.522563: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:01:38.522774: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:01:38.524299: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-01 02:01:38.524324: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-01 02:01:38.524334: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-01 02:01:38.532404: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9842 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-04-01 02:01:39.038403: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:01:39.038486: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:01:39.038504: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:01:39.038519: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:01:39.038534: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:01:39.038548: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:01:39.038563: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:01:39.038577: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:01:39.039885: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:01:39.041110: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:01:39.041147: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:01:39.041163: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:01:39.041177: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:01:39.041202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:01:39.041217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:01:39.041230: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:01:39.041245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:01:39.042515: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:01:39.042550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-01 02:01:39.042559: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-01 02:01:39.042567: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-01 02:01:39.043929: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9842 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl3783 thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) {'thcl': {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'], 'list_hashtags_csv': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'svm_hashtag_type_desc': 5972, 'photo_desc_type': 5972, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_entrant_syctomXV_111023 NUM_CLASSES 11 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_entrant_syctomXV_111023 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-04-01 02:01:55.053753: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:01:55.371455: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:01:57.533109: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.533750: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.534258: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.534762: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.535299: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.535807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.536315: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.536488: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.537609: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.537627: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.560774: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.560806: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.561324: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.561339: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.573592: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.573621: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.574138: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.574154: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.672004: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.672060: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.672582: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.672599: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.684327: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.684370: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.684892: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.684921: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-01 02:01:57.785045: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.785598: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.789034: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.789561: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.872557: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.873122: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.878249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.878787: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.965004: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.965564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.971257: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:57.971792: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.004135: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.004680: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.009842: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.010366: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.041975: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.042509: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.056518: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.057050: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.283949: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.284488: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.284995: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.285532: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.328063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.328595: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.479794: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.480347: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.480867: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.481385: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.548060: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.548627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.549152: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.549678: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.587334: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.587917: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.597054: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.597648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.609835: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.610395: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.614509: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.615065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.615599: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.616139: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.616932: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.617469: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.629221: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.629783: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.630348: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.630894: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.631473: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.632013: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.632554: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.633091: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.654731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.655332: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.701150: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.701716: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.794692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.795300: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.795861: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.796401: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.826601: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.827177: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.861071: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.861633: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.862164: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.862690: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.874046: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.874615: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.875163: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.875692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.878519: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.878537: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-04-01 02:01:58.892375: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.893155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.921043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.921883: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.922680: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.923485: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.924222: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-01 02:01:58.924963: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_entrant_syctomXV_111023 /data/models_weight/learn_entrant_syctomXV_111023/mask_model.h5 size_local : 256052544 size in s3 : 256052544 create time local : 2023-10-26 16:36:43 create time in s3 : 2023-10-11 13:57:17 mask_model.h5 already exist and didn't need to update list_images length : 8 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.60000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 13 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.47500 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.03750 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 3 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.22500 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 7 Detection mask done ! Trying to reset tf kernel 2340196 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 555 tf kernel not reseted sub process len(results) : 8 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 8 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1748 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3783 Catched exception ! Connect or reconnect ! thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] time for calcul the mask position with numpy : 0.03646993637084961 nb_pixel_total : 668582 time to create 1 rle with new method : 0.22394013404846191 length of segment : 1694 time for calcul the mask position with numpy : 0.0034198760986328125 nb_pixel_total : 137236 time to create 1 rle with old method : 0.18415594100952148 length of segment : 460 time for calcul the mask position with numpy : 0.002716064453125 nb_pixel_total : 129387 time to create 1 rle with old method : 0.1594681739807129 length of segment : 860 time for calcul the mask position with numpy : 0.002762317657470703 nb_pixel_total : 52088 time to create 1 rle with old method : 0.06192374229431152 length of segment : 322 time for calcul the mtime to create 1 rle with new method : 0.7418375015258789 length of segment : 582 time for calcul the mask position with numpy : 0.0025577545166015625 nb_pixel_total : 76664 time to create 1 rle with old method : 0.11327695846557617 length of segment : 424 time for calcul the mask position with numpy : 0.0025098323822021484 nb_pixel_total : 103243 time to create 1 rle with old method : 0.12595534324645996 length of segment : 380 time for calcul the mask position with numpy : 0.002115964889526367 nb_pixel_total : 76322 time to create 1 rle with old method : 0.09284329414367676 length of segment : 437 time for calcul the mask position with numpy : 0.0005130767822265625 nb_pixel_total : 15591 time to create 1 rle with old method : 0.022216796875 length of segment : 164 time for calcul the mask position with numpy : 0.1589357852935791 nb_pixel_total : 1050340 time to create 1 rle with new method : 0.3600783348083496 length of segment : 3446 time for calcul the mask position with numpy : 0.001190185546875 nb_pixel_total : 56087 time to create 1 rle with old method : 0.06764674186706543 length of segment : 219 time for calcul the mask position with numpy : 0.0007543563842773438 nb_pixel_total : 7157 time to create 1 rle with old method : 0.00911092758178711 length of segment : 199 time for calcul the mask position with numpy : 0.00035834312438964844 nb_pixel_total : 6535 time to create 1 rle with old method : 0.008159875869750977 length of segment : 90 time for calcul the mask position with numpy : 0.0007762908935546875 nb_pixel_total : 54642 time to create 1 rle with old method : 0.07071852684020996 length of segment : 220 time for calcul the mask position with numpy : 0.0010998249053955078 nb_pixel_total : 17384 time to create 1 rle with old method : 0.028680801391601562 length of segment : 192 time for calcul the mask position with numpy : 0.0074231624603271484 nb_pixel_total : 335990 time to create 1 rle with new method : 0.0406954288482666 length of segment : 824 time for calcul the mask position with numpy : 0.007380008697509766 nb_pixel_total : 433423 time to create 1 rle with new method : 0.018797874450683594 length of segment : 1266 time for calcul the mask position with numpy : 0.0012700557708740234 nb_pixel_total : 47363 time to create 1 rle with old method : 0.056032419204711914 length of segment : 261 time for calcul the mask position with numpy : 0.0015187263488769531 nb_pixel_total : 36319 time to create 1 rle with old method : 0.04364371299743652 length of segment : 316 time for calcul the mask position with numpy : 0.0020973682403564453 nb_pixel_total : 89651 time to create 1 rle with old method : 0.1070859432220459 length of segment : 186 time for calcul the mask position with numpy : 0.025339365005493164 nb_pixel_total : 831713 time to create 1 rle with new method : 0.18060755729675293 length of segment : 1739 time for calcul the mask position with numpy : 0.0021047592163085938 nb_pixel_total : 62703 time to create 1 rle with old method : 0.07715678215026855 length of segment : 271 time for calcul the mask position with numpy : 0.0043294429779052734 nb_pixel_total : 148677 time to create 1 rle with old method : 0.17569708824157715 length of segment : 511 time for calcul the mask position with numpy : 0.13132190704345703 nb_pixel_total : 2242469 time to create 1 rle with new method : 0.19413971900939941 length of segment : 2355 time for calcul the mask position with numpy : 0.004461050033569336 nb_pixel_total : 109829 time to create 1 rle with old method : 0.1429591178894043 length of segment : 579 time for calcul the mask position with numpy : 0.42628049850463867 nb_pixel_total : 3455220 time to create 1 rle with new method : 0.7742111682891846 length of segment : 2189 time for calcul the mask position with numpy : 0.0010197162628173828 nb_pixel_total : 9207 time to create 1 rle with old method : 0.011457204818725586 length of segment : 115 time for calcul the mask position with numpy : 0.5138919353485107 nb_pixel_total : 4277379 time to create 1 rle with new method : 0.7090897560119629 length of segment : 1653 time for calcul the mask position with numpy : 0.002286195755004883 nb_pixel_total : 55287 time to create 1 rle with old method : 0.06951165199279785 length of segment : 285 time for calcul the mask position with numpy : 0.0014278888702392578 nb_pixel_total : 15597 time to create 1 rle with old method : 0.022199392318725586 length of segment : 159 time spent for convertir_results : 19.87170720100403 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 65 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 87.98178434371948 time spend to save output : 0.11380481719970703 total time spend for step 1 : 88.09558916091919 step2:mask_detect Tue Apr 1 02:03:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 5525 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-04-01 02:03:07.251102: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-04-01 02:03:07.283142: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-04-01 02:03:07.285279: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3e58000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-04-01 02:03:07.285321: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-04-01 02:03:07.292163: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-04-01 02:03:07.460219: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2d730b60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-04-01 02:03:07.460274: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-04-01 02:03:07.461299: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:03:07.463011: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:03:07.471879: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:03:07.488959: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:03:07.491709: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:03:07.504784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:03:07.509199: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:03:07.544269: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:03:07.545773: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:03:07.546276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:03:07.547477: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-01 02:03:07.547498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-01 02:03:07.547507: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-01 02:03:07.549474: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5051 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-04-01 02:03:07.778993: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:03:07.779172: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:03:07.779224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:03:07.779297: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:03:07.779344: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:03:07.779382: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:03:07.779406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:03:07.779430: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:03:07.781116: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:03:07.783447: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-04-01 02:03:07.783587: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-01 02:03:07.783635: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:03:07.783695: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-01 02:03:07.783744: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-01 02:03:07.783794: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-01 02:03:07.783841: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-01 02:03:07.783899: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-01 02:03:07.785416: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-01 02:03:07.785494: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-01 02:03:07.785514: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-01 02:03:07.785531: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-01 02:03:07.786892: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5051 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl3453 thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) {'thcl': {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'svm_hashtag_type_desc': 5732, 'photo_desc_type': 5732, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME mask_refus_amiens_050123 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : mask_refus_amiens_050123 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-04-01 02:03:24.132659: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-01 02:03:24.540728: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/mask_refus_amiens_050123 /data/models_weight/mask_refus_amiens_050123/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2023-01-05 13:44:07 create time in s3 : 2023-01-05 12:23:52 mask_model.h5 already exist and didn't need to update list_images length : 8 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.60000 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 16 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 69 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 41 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.47500 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 61 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.03750 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 49 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 44 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.22500 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 26 Detection mask done ! Trying to reset tf kernel 2350003 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5525 tf kernel not reseted sub process len(results) : 8 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 8 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 10814 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3453 Catched exception ! Connect or reconnect ! thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.01613330841064453 nb_pixel_total : 454665 time to create 1 rle with new method : 0.07406401634216309 length of segment : 992 time for calcul the mask position with numpy : 0.030806779861450195 nb_pixel_total : 1607687 time to create 1 rle with new method : 0.42232394218444824 length of segment : 2423 time for calcul the mask position with numpy : 0.0020182132720947266 nb_pixel_total : 118986 time to create 1 rle with old method : 0.20745587348937988 length of segment : 445 time for calcul the mask position with numpy : 0.0028672218322753906 nb_pixel_total : 161846 time to create 1 rle with new method : 0.009042501449584961 length of segment : 471 time for calcul the mask position with numpy : 0.004271745681762695 nb_pixel_total : 205434 time to create 1 rle with new method : 0.010059118270874023 length of segment : 768 time for calcul the mask position with numpy : 0.007875204086303711 nb_pixel_total : 395146 time to create 1 rle with new method : 0.029527664184570312 length of segment : 907 time for calcul the mask position with numpy : 0.006925106048583984 nb_pixel_total : 246621 time to create 1 rle with new method : 0.018489360809326172 length of segment : 931 time for calcul the mask position with numpy : 0.4034128189086914 nb_pixel_total : 2820837 time to create 1 rle with new method : 1.161987066268921 length of segment : 2599 time for calcul the mask position with numpy : 0.013940572738647461 nb_pixel_total : 733846 time to create 1 rle with new method : 0.22456097602844238 length of segment : 995 time for calcul the mask position with numpy : 0.0030193328857421875 nb_pixel_total : 113251 time to create 1 rle with old method : 0.13490843772888184 length of segment : 606 time for calcul the mask position with numpy : 0.010979890823364258 nb_pixel_total : 479127 time to create 1 rle with new method : 0.07775163650512695 length of segment : 974 time for calcul the mask position with numpy : 0.005869388580322266 nb_pixel_total : 331978 time to create 1 rle with new method : 0.015719890594482422 length of segment : 1092 time for calcul the mask position with numpy : 0.02736663818359375 nb_pixel_total : 1200545 time to create 1 rle with new method : 0.10976672172546387 length of segment : 1730 time for calcul the mask position with numpy : 0.006974935531616211 nb_pixel_total : 200806 time to create 1 rle with new method : 0.015291213989257812 length of segment : 805 time for calcul the mask position with numpy : 0.0022706985473632812 nb_pixel_total : 133238 time to create 1 rle with old method : 0.1664130687713623 length of segment : 306 time for calcul the mask position with numpy : 0.5267281532287598 nb_pixel_total : 4501170 time to create 1 rle with new method : 0.8794171810150146 length of segment : 3574 time for calcul the mask position with numpy : 0.0071563720703125 nb_pixel_total : 196521 time to create 1 rle with new method : 0.012934684753417969 length of segment : 467 time for calcul the mask position with numpy : 0.0006186962127685547 nb_pixel_total : 23610 time to create 1 rle with old method : 0.030208587646484375 length of segment : 152 time for calcul the mask position with numpy : 0.020638704299926758 nb_pixel_total : 873082 time to create 1 rle with new method : 0.07998490333557129 length of segment : 917 time for calcul the mask position with numpy : 0.0029141902923583984 nb_pixel_total : 74110 time to create 1 rle with old method : 0.09604954719543457 length of segment : 409 time for calcul the mask position with numpy : 0.006136178970336914 nb_pixel_total : 274616 time to create 1 rle with new method : 0.017066001892089844 length of segment : 796 time for calcul the mask position with numpy : 0.005471706390380859 nb_pixel_total : 235290 time to create 1 rle with new method : 0.014846324920654297 length of segment : 891 time for calcul the mask position with numpy : 0.005484342575073242 nb_pixel_total : 249786 time to create 1 rle with new method : 0.013924121856689453 length of segment : 844 time for calcul the mask position with numpy : 0.002570629119873047 nb_pixel_total : 83833 time to create 1 rle with old method : 0.10523247718811035 length of segment : 454 time for calcul the mask position with numpy : 0.00223541259765625 nb_pixel_total : 85464 time to create 1 rle with old method : 0.10163664817810059 length of segment : 336 time for calcul the mask position with numpy : 0.004312992095947266 nb_pixel_total : 110151 time to create 1 rle with old method : 0.13565921783447266 length of segment : 519 time for calcul the mask position with numpy : 0.008486270904541016 nb_pixel_total : 123277 time to create 1 rle with old method : 0.14849615097045898 length of segment : 424 time for calcul the mask position with numpy : 0.028351783752441406 nb_pixel_total : 503535 time to create 1 rle with new method : 0.06990885734558105 length of segment : 849 time for calcul the mask position with numpy : 0.007010698318481445 nb_pixel_total : 109450 time to create 1 rle with old method : 0.1515190601348877 length of segment : 330 time for calcul the mask position with numpy : 0.0177309513092041 nb_pixel_total : 831366 time to create 1 rle with new method : 0.27272820472717285 length of segment : 677 time for calcul the mask position with numpy : 0.004868984222412109 nb_pixel_total : 215703 time to create 1 rle with new method : 0.011329412460327148 length of segment : 720 time for calcul the mask position with numpy : 0.0061948299407958984 nb_pixel_total : 243117 time to create 1 rle with new method : 0.015653133392333984 length of segment : 726 time for calcul the mask position with numpy : 0.023177623748779297 nb_pixel_total : 733144 time to create 1 rle with new method : 0.1203312873840332 length of segment : 1330 time for calcul the mask position with numpy : 0.00417327880859375 nb_pixel_total : 145669 time to create 1 rle with old method : 0.1924445629119873 length of segment : 598 time for calcul the mask position with numpy : 0.02152109146118164 nb_pixel_total : 587168 time to create 1 rle with new method : 0.058060407638549805 length of segment : 1083 time for calcul the mask position with numpy : 0.002964019775390625 nb_pixel_total : 108804 time to create 1 rle with old method : 0.129319429397583 length of segment : 367 time for calcul the mask position with numpy : 0.0017161369323730469 nb_pixel_total : 68282 time to create 1 rle with old method : 0.08494877815246582 length of segment : 290 time for calcul the mask position with numpy : 0.001062631607055664 nb_pixel_total : 26531 time to create 1 rle with old method : 0.03562211990356445 length of segment : 167 time for calcul the mask position with numpy : 0.0009930133819580078 nb_pixel_total : 51496 time to create 1 rle with old method : 0.06594038009643555 length of segment : 239 time for calcul the mask position with numpy : 0.003518342971801758 nb_pixel_total : 91210 time to create 1 rle with old method : 0.1303548812866211 length of segment : 417 time for calcul the mask position with numpy : 0.0021469593048095703 nb_pixel_total : 67061 time to create 1 rle with old method : 0.08000373840332031 length of segment : 296 time for calcul the mask position with numpy : 0.0008714199066162109 nb_pixel_total : 29514 time to create 1 rle with old method : 0.03550362586975098 length of segment : 203 time for calcul the mask position with numpy : 0.003662586212158203 nb_pixel_total : 114136 time to create 1 rle with old method : 0.13435959815979004 length of segment : 366 time for calcul the mask position with numpy : 0.0015223026275634766 nb_pixel_total : 46421 time to create 1 rle with old method : 0.07700085639953613 length of segment : 272 time for calcul the mask position with numpy : 0.0022516250610351562 nb_pixel_total : 58188 time to create 1 rle with old method : 0.07529711723327637 length of segment : 209 time for calcul the mask position with numpy : 0.0005326271057128906 nb_pixel_total : 25119 time to create 1 rle with old method : 0.030424118041992188 length of segment : 148 time for calcul the mask position with numpy : 0.010380744934082031 nb_pixel_total : 263167 time to create 1 rle with new method : 0.017282724380493164 length of segment : 624 time for calcul the mask position with numpy : 0.0014951229095458984 nb_pixel_total : 58931 time to create 1 rle with old method : 0.07008194923400879 length of segment : 301 time for calcul the mask position with numpy : 0.003080129623413086 nb_pixel_total : 75867 time to create 1 rle with old method : 0.08957600593566895 length of segment : 289 time for calcul the mask position with numpy : 0.0017380714416503906 nb_pixel_total : 54536 time to create 1 rle with old method : 0.06873154640197754 length of segment : 340 time for calcul the mask position with numpy : 0.0009226799011230469 nb_pixel_total : 22708 time to create 1 rle with old method : 0.028065204620361328 length of segment : 176 time for calcul the mask position with numpy : 0.0011777877807617188 nb_pixel_total : 46078 time to create 1 rle with old method : 0.05511760711669922 length of segment : 321 time for calcul the mask position with numpy : 0.005146026611328125 nb_pixel_total : 137030 time to create 1 rle with old method : 0.15974831581115723 length of segment : 939 time for calcul the mask position with numpy : 0.0183413028717041 nb_pixel_total : 541754 time to create 1 rle with new method : 0.07558941841125488 length of segment : 898 time for calcul the mask position with numpy : 0.006959438323974609 nb_pixel_total : 48227 time to create 1 rle with old method : 0.05733633041381836 length of segment : 291 time for calcul the mask position with numpy : 0.009681463241577148 nb_pixel_total : 317301 time to create 1 rle with new method : 0.031090736389160156 length of segment : 660 time for calcul the mask position with numpy : 0.003214120864868164 nb_pixel_total : 111320 time to create 1 rle with old method : 0.13226580619812012 length of segment : 388 time for calcul the mask position with numpy : 0.002457141876220703 nb_pixel_total : 76098 time to create 1 rle with old method : 0.09182929992675781 length of segment : 557 time for calcul the mask position with numpy : 0.004461765289306641 nb_pixel_total : 165123 time to create 1 rle with new method : 0.011760711669921875 length of segment : 375 time for calcul the mask position with numpy : 0.002406597137451172 nb_pixel_total : 78865 time to create 1 rle with old method : 0.11995220184326172 length of segment : 354 time for calcul the mask position with numpy : 0.002535104751586914 nb_pixel_total : 70501 time to create 1 rle with old method : 0.08809018135070801 length of segment : 394 time for calcul the mask position with numpy : 0.003088235855102539 nb_pixel_total : 87046 time to create 1 rle with old method : 0.10156941413879395 length of segment : 639 time for calcul the mask position with numpy : 0.014241695404052734 nb_pixel_total : 496592 time to create 1 rle with new method : 0.043012142181396484 length of segment : 875 time for calcul the mask position with numpy : 0.0030858516693115234 nb_pixel_total : 61926 time to create 1 rle with old method : 0.07536530494689941 length of segment : 389 time for calcul the mask position with numpy : 0.0018558502197265625 nb_pixel_total : 77380 time to create 1 rle with old method : 0.1191258430480957 length of segment : 294 time for calcul the mask position with numpy : 0.005511760711669922 nb_pixel_total : 185133 time to create 1 rle with new method : 0.017044782638549805 length of segment : 560 time for calcul the mask position with numpy : 0.001706838607788086 nb_pixel_total : 68223 time to create 1 rle with old method : 0.07999777793884277 length of segment : 203 time for calcul the mask position with numpy : 0.00556635856628418 nb_pixel_total : 196581 time to create 1 rle with new method : 0.01992511749267578 length of segment : 595 time for calcul the mask position with numpy : 0.0018684864044189453 nb_pixel_total : 87506 time to create 1 rle with old method : 0.1040189266204834 length of segment : 339 time for calcul the mask position with numpy : 0.0065076351165771484 nb_pixel_total : 307565 time to create 1 rle with new method : 0.02476811408996582 length of segment : 845 time for calcul the mask position with numpy : 0.002711057662963867 nb_pixel_total : 69207 time to create 1 rle with old method : 0.11000990867614746 length of segment : 384 time for calcul the mask position with numpy : 0.007114410400390625 nb_pixel_total : 233939 time to create 1 rle with new method : 0.021408557891845703 length of segment : 603 time for calcul the mask position with numpy : 0.009662389755249023 nb_pixel_total : 400670 time to create 1 rle with new method : 0.027283668518066406 length of segment : 840 time for calcul the mask position with numpy : 0.015293121337890625 nb_pixel_total : 500281 time to create 1 rle with new method : 0.05485105514526367 length of segment : 1055 time for calcul the mask position with numpy : 0.0074329376220703125 nb_pixel_total : 131296 time to create 1 rle with old method : 0.15472126007080078 length of segment : 482 time for calcul the mask position with numpy : 0.02086806297302246 nb_pixel_total : 347077 time to create 1 rle with new method : 0.03110647201538086 length of segment : 692 time for calcul the mask position with numpy : 0.0017821788787841797 nb_pixel_total : 76880 time to create 1 rle with old method : 0.09210968017578125 length of segment : 325 time for calcul the mask position with numpy : 0.008033275604248047 nb_pixel_total : 330082 time to create 1 rle with new method : 0.02770090103149414 length of segment : 846 time for calcul the mask position with numpy : 0.003202676773071289 nb_pixel_total : 115974 time to create 1 rle with old method : 0.13750123977661133 length of segment : 372 time for calcul the mask position with numpy : 0.006573677062988281 nb_pixel_total : 187168 time to create 1 rle with new method : 0.020468711853027344 length of segment : 536 time for calcul the mask position with numpy : 0.0027856826782226562 nb_pixel_total : 72731 time to create 1 rle with old method : 0.11006593704223633 length of segment : 395 time for calcul the mask position with numpy : 0.012433767318725586 nb_pixel_total : 349880 time to create 1 rle with new method : 0.031977176666259766 length of segment : 692 time for calcul the mask position with numpy : 0.002389669418334961 nb_pixel_total : 82339 time to create 1 rle with old method : 0.09586095809936523 length of segment : 714 time for calcul the mask position with numpy : 0.0017201900482177734 nb_pixel_total : 69904 time to create 1 rle with old method : 0.08470940589904785 length of segment : 297 time for calcul the mask position with numpy : 0.0018703937530517578 nb_pixel_total : 73851 time to create 1 rle with old method : 0.09938168525695801 length of segment : 234 time for calcul the mask position with numpy : 0.04766392707824707 nb_pixel_total : 52380 time to create 1 rle with old method : 0.08609890937805176 length of segment : 221 time for calcul the mask position with numpy : 0.05232095718383789 nb_pixel_total : 1219082 time to create 1 rle with new method : 0.2629547119140625 length of segment : 1135 time for calcul the mask position with numpy : 0.1020207405090332 nb_pixel_total : 254073 time to create 1 rle with new method : 0.12814903259277344 length of segment : 621 time for calcul the mask position with numpy : 0.0026307106018066406 nb_pixel_total : 66985 time to create 1 rle with old method : 0.08149909973144531 length of segment : 464 time for calcul the mask position with numpy : 0.019256591796875 nb_pixel_total : 207029 time to create 1 rle with new method : 0.01810598373413086 length of segment : 612 time for calcul the mask position with numpy : 0.040062904357910156 nb_pixel_total : 241231 time to create 1 rle with new method : 0.014677762985229492 length of segment : 544 time for calcul the mask position with numpy : 0.011137008666992188 nb_pixel_total : 160780 time to create 1 rle with new method : 0.010282278060913086 length of segment : 421 time for calcul the mask position with numpy : 0.004392147064208984 nb_pixel_total : 87077 time to create 1 rle with old method : 0.10773205757141113 length of segment : 318 time for calcul the mask position with numpy : 0.02447342872619629 nb_pixel_total : 289784 time to create 1 rle with new method : 0.019991636276245117 length of segment : 796 time for calcul the mask position with numpy : 0.0055675506591796875 nb_pixel_total : 247886 time to create 1 rle with new method : 0.013494491577148438 length of segment : 488 time for calcul the mask position with numpy : 0.003030061721801758 nb_pixel_total : 83236 time to create 1 rle with old method : 0.09997320175170898 length of segment : 374 time for calcul the mask position with numpy : 0.00995635986328125 nb_pixel_total : 112643 time to create 1 rle with old method : 0.13845396041870117 length of segment : 782 time for calcul the mask position with numpy : 0.006824970245361328 nb_pixel_total : 163432 time to create 1 rle with new method : 0.01201486587524414 length of segment : 745 time for calcul the mask position with numpy : 0.0034928321838378906 nb_pixel_total : 59493 time to create 1 rle with old method : 0.07222843170166016 length of segment : 183 time for calcul the mask position with numpy : 0.05415010452270508 nb_pixel_total : 492131 time to create 1 rle with new method : 0.35210466384887695 length of segment : 1731 time for calcul the mask position with numpy : 0.029969215393066406 nb_pixel_total : 71878 time to create 1 rle with old method : 0.09909248352050781 length of segment : 409 time for calcul the mask position with numpy : 0.007300615310668945 nb_pixel_total : 124173 time to create 1 rle with old method : 0.16028666496276855 length of segment : 353 time for calcul the mask position with numpy : 0.03706765174865723 nb_pixel_total : 467676 time to create 1 rle with new method : 0.301297664642334 length of segment : 653 time for calcul the mask position with numpy : 0.005866289138793945 nb_pixel_total : 189912 time to create 1 rle with new method : 0.01224207878112793 length of segment : 404 time for calcul the mask position with numpy : 0.00044846534729003906 nb_pixel_total : 14784 time to create 1 rle with old method : 0.04370689392089844 length of segment : 143 time for calcul the mask position with numpy : 0.0037903785705566406 nb_pixel_total : 93760 time to create 1 rle with old method : 0.12170290946960449 length of segment : 413 time for calcul the mask position with numpy : 0.0020148754119873047 nb_pixel_total : 35691 time to create 1 rle with old method : 0.04422736167907715 length of segment : 307 time for calcul the mask position with numpy : 0.014973878860473633 nb_pixel_total : 409885 time to create 1 rle with new method : 0.06701087951660156 length of segment : 982 time for calcul the mask position with numpy : 0.006397724151611328 nb_pixel_total : 128781 time to create 1 rle with old method : 0.16689443588256836 length of segment : 472 time for calcul the mask position with numpy : 0.003447294235229492 nb_pixel_total : 71223 time to create 1 rle with old method : 0.08655905723571777 length of segment : 150 time for calcul the mask position with numpy : 0.0007793903350830078 nb_pixel_total : 19276 time to create 1 rle with old method : 0.029775142669677734 length of segment : 275 time for calcul the mask position with numpy : 0.04014325141906738 nb_pixel_total : 589447 time to create 1 rle with new method : 0.03110957145690918 length of segment : 862 time for calcul the mask position with numpy : 0.05700349807739258 nb_pixel_total : 652290 time to create 1 rle with new method : 0.2415013313293457 length of segment : 1955 time for calcul the mask position with numpy : 0.04095816612243652 nb_pixel_total : 907709 time to create 1 rle with new method : 0.31308412551879883 length of segment : 871 time for calcul the mask position with numpy : 0.0014081001281738281 nb_pixel_total : 31396 time to create 1 rle with old method : 0.042351484298706055 length of segment : 427 time for calcul the mask position with numpy : 0.005092620849609375 nb_pixel_total : 209568 time to create 1 rle with new method : 0.015176534652709961 length of segment : 373 time for calcul the mask position with numpy : 0.01722574234008789 nb_pixel_total : 875897 time to create 1 rle with new method : 0.2896735668182373 length of segment : 869 time for calcul the mask position with numpy : 0.0017619132995605469 nb_pixel_total : 69055 time to create 1 rle with old method : 0.08138394355773926 length of segment : 269 time for calcul the mask position with numpy : 0.001708984375 nb_pixel_total : 44849 time to create 1 rle with old method : 0.05652022361755371 length of segment : 196 time for calcul the mask position with numpy : 0.001764059066772461 nb_pixel_total : 83081 time to create 1 rle with old method : 0.10017609596252441 length of segment : 415 time for calcul the mask position with numpy : 0.0016503334045410156 nb_pixel_total : 45941 time to create 1 rle with old method : 0.05661606788635254 length of segment : 216 time for calcul the mask position with numpy : 0.0018758773803710938 nb_pixel_total : 64460 time to create 1 rle with old method : 0.08023953437805176 length of segment : 371 time for calcul the mask position with numpy : 0.0009543895721435547 nb_pixel_total : 24846 time to create 1 rle with old method : 0.03568553924560547 length of segment : 232 time for calcul the mask position with numpy : 0.000865936279296875 nb_pixel_total : 17428 time to create 1 rle with old method : 0.022347688674926758 length of segment : 265 time for calcul the mask position with numpy : 0.019597768783569336 nb_pixel_total : 116945 time to create 1 rle with old method : 0.17322254180908203 length of segment : 437 time for calcul the mask position with numpy : 0.008203268051147461 nb_pixel_total : 336525 time to create 1 rle with new method : 0.1645066738128662 length of segment : 439 time for calcul the mask position with numpy : 0.014925241470336914 nb_pixel_total : 374057 time to create 1 rle with new method : 0.03619384765625 length of segment : 669 time for calcul the mask position with numpy : 0.001041412353515625 nb_pixel_total : 44742 time to create 1 rle with old method : 0.05458545684814453 length of segment : 200 time for calcul the mask position with numpy : 0.22966957092285156 nb_pixel_total : 742833 time to create 1 rle with new method : 0.11186099052429199 length of segment : 1029 time for calcul the mask position with numpy : 0.26102304458618164 nb_pixel_total : 907926 time to create 1 rle with new method : 0.05164766311645508 length of segment : 980 time for calcul the mask position with numpy : 0.0011539459228515625 nb_pixel_total : 42165 time to create 1 rle with old method : 0.06264090538024902 length of segment : 216 time for calcul the mask position with numpy : 0.004434823989868164 nb_pixel_total : 144488 time to create 1 rle with old method : 0.20236945152282715 length of segment : 620 time for calcul the mask position with numpy : 0.05953502655029297 nb_pixel_total : 293614 time to create 1 rle with new method : 0.03721737861633301 length of segment : 951 time for calcul the mask position with numpy : 0.00799560546875 nb_pixel_total : 274436 time to create 1 rle with new method : 0.015340089797973633 length of segment : 658 time for calcul the mask position with numpy : 0.0013515949249267578 nb_pixel_total : 32101 time to create 1 rle with old method : 0.03783130645751953 length of segment : 181 time for calcul the mask position with numpy : 0.014739036560058594 nb_pixel_total : 95789 time to create 1 rle with old method : 0.11949324607849121 length of segment : 505 time for calcul the mask position with numpy : 0.0012133121490478516 nb_pixel_total : 21846 time to create 1 rle with old method : 0.02649235725402832 length of segment : 195 time for calcul the mask position with numpy : 0.013261795043945312 nb_pixel_total : 43645 time to create 1 rle with old method : 0.05632829666137695 length of segment : 217 time for calcul the mask position with numpy : 0.022414445877075195 nb_pixel_total : 346611 time to create 1 rle with new method : 0.020072221755981445 length of segment : 861 time for calcul the mask position with numpy : 0.001050710678100586 nb_pixel_total : 18331 time to create 1 rle with old method : 0.022790908813476562 length of segment : 125 time for calcul the mask position with numpy : 0.1101834774017334 nb_pixel_total : 146426 time to create 1 rle with old method : 0.21047520637512207 length of segment : 547 time for calcul the mask position with numpy : 0.0017719268798828125 nb_pixel_total : 33680 time to create 1 rle with old method : 0.06172657012939453 length of segment : 292 time for calcul the mask position with numpy : 0.16065740585327148 nb_pixel_total : 348264 time to create 1 rle with new method : 0.05467081069946289 length of segment : 806 time for calcul the mask position with numpy : 0.013091325759887695 nb_pixel_total : 225738 time to create 1 rle with new method : 0.030063390731811523 length of segment : 653 time for calcul the mask position with numpy : 0.04219985008239746 nb_pixel_total : 45449 time to create 1 rle with old method : 0.08587026596069336 length of segment : 337 time for calcul the mask position with numpy : 0.02057647705078125 nb_pixel_total : 399635 time to create 1 rle with new method : 0.02959895133972168 length of segment : 832 time for calcul the mask position with numpy : 0.09704232215881348 nb_pixel_total : 312121 time to create 1 rle with new method : 0.03932619094848633 length of segment : 1136 time for calcul the mask position with numpy : 0.4150056838989258 nb_pixel_total : 1699798 time to create 1 rle with new method : 0.7515535354614258 length of segment : 2325 time for calcul the mask position with numpy : 0.0009927749633789062 nb_pixel_total : 21261 time to create 1 rle with old method : 0.025604724884033203 length of segment : 215 time for calcul the mask position with numpy : 0.0010557174682617188 nb_pixel_total : 27759 time to create 1 rle with old method : 0.033205509185791016 length of segment : 280 time for calcul the mask position with numpy : 0.0007905960083007812 nb_pixel_total : 24896 time to create 1 rle with old method : 0.03013157844543457 length of segment : 147 time for calcul the mask position with numpy : 0.029244661331176758 nb_pixel_total : 255037 time to create 1 rle with new method : 0.020653247833251953 length of segment : 828 time for calcul the mask position with numpy : 0.0018506050109863281 nb_pixel_total : 38163 time to create 1 rle with old method : 0.04481697082519531 length of segment : 219 time for calcul the mask position with numpy : 0.012675762176513672 nb_pixel_total : 76887 time to create 1 rle with old method : 0.09834504127502441 length of segment : 407 time for calcul the mask position with numpy : 0.0017819404602050781 nb_pixel_total : 66127 time to create 1 rle with old method : 0.07998418807983398 length of segment : 215 time for calcul the mask position with numpy : 0.020078659057617188 nb_pixel_total : 344922 time to create 1 rle with new method : 0.021784543991088867 length of segment : 495 time for calcul the mask position with numpy : 0.015917539596557617 nb_pixel_total : 147018 time to create 1 rle with old method : 0.1762685775756836 length of segment : 359 time for calcul the mask position with numpy : 0.0004062652587890625 nb_pixel_total : 4476 time to create 1 rle with old method : 0.005797386169433594 length of segment : 198 time for calcul the mask position with numpy : 0.0029306411743164062 nb_pixel_total : 108688 time to create 1 rle with old method : 0.1283862590789795 length of segment : 703 time for calcul the mask position with numpy : 0.004694223403930664 nb_pixel_total : 123013 time to create 1 rle with old method : 0.14585065841674805 length of segment : 398 time for calcul the mask position with numpy : 0.0096282958984375 nb_pixel_total : 307480 time to create 1 rle with new method : 0.025596141815185547 length of segment : 463 time for calcul the mask position with numpy : 0.010464906692504883 nb_pixel_total : 163462 time to create 1 rle with new method : 0.015360593795776367 length of segment : 668 time for calcul the mask position with numpy : 0.020618438720703125 nb_pixel_total : 697111 time to create 1 rle with new method : 0.04488563537597656 length of segment : 1239 time for calcul the mask position with numpy : 0.0021991729736328125 nb_pixel_total : 93852 time to create 1 rle with old method : 0.13219928741455078 length of segment : 285 time for calcul the mask position with numpy : 0.001684427261352539 nb_pixel_total : 54537 time to create 1 rle with old method : 0.06403779983520508 length of segment : 312 time for calcul the mask position with numpy : 0.003046751022338867 nb_pixel_total : 131838 time to create 1 rle with old method : 0.18315362930297852 length of segment : 378 time for calcul the mask position with numpy : 0.0012044906616210938 nb_pixel_total : 6489 time to create 1 rle with old method : 0.008003711700439453 length of segment : 118 time for calcul the mask position with numpy : 0.001096963882446289 nb_pixel_total : 30335 time to create 1 rle with old method : 0.03711533546447754 length of segment : 299 time for calcul the mask position with numpy : 0.0016171932220458984 nb_pixel_total : 72597 time to create 1 rle with old method : 0.13403725624084473 length of segment : 213 time for calcul the mask position with numpy : 0.001249551773071289 nb_pixel_total : 26043 time to create 1 rle with old method : 0.03150367736816406 length of segment : 270 time for calcul the mask position with numpy : 0.0018415451049804688 nb_pixel_total : 39595 time to create 1 rle with old method : 0.04965400695800781 length of segment : 297 time for calcul the mask position with numpy : 0.004530906677246094 nb_pixel_total : 151254 time to create 1 rle with new method : 0.009453058242797852 length of segment : 591 time for calcul the mask position with numpy : 0.0023941993713378906 nb_pixel_total : 68744 time to create 1 rle with old method : 0.08002376556396484 length of segment : 327 time for calcul the mask position with numpy : 0.028048276901245117 nb_pixel_total : 272024 time to create 1 rle with new method : 0.02055072784423828 length of segment : 587 time for calcul the mask position with numpy : 0.002646923065185547 nb_pixel_total : 101988 time to create 1 rle with old method : 0.13565468788146973 length of segment : 372 time for calcul the mask position with numpy : 0.004457235336303711 nb_pixel_total : 149072 time to create 1 rle with old method : 0.1744534969329834 length of segment : 365 time for calcul the mask position with numpy : 0.014172554016113281 nb_pixel_total : 192864 time to create 1 rle with new method : 0.027858495712280273 length of segment : 541 time for calcul the mask position with numpy : 0.004054069519042969 nb_pixel_total : 167971 time to create 1 rle with new method : 0.012656211853027344 length of segment : 501 time for calcul the mask position with numpy : 0.017203569412231445 nb_pixel_total : 335973 time to create 1 rle with new method : 0.041344404220581055 length of segment : 735 time for calcul the mask position with numpy : 0.0017371177673339844 nb_pixel_total : 77424 time to create 1 rle with old method : 0.09235310554504395 length of segment : 206 time for calcul the mask position with numpy : 0.002585887908935547 nb_pixel_total : 76674 time to create 1 rle with old method : 0.09071683883666992 length of segment : 625 time for calcul the mask position with numpy : 0.005385160446166992 nb_pixel_total : 163364 time to create 1 rle with new method : 0.016069650650024414 length of segment : 473 time for calcul the mask position with numpy : 0.003592252731323242 nb_pixel_total : 164318 time to create 1 rle with new method : 0.011739253997802734 length of segment : 482 time for calcul the mask position with numpy : 0.0011286735534667969 nb_pixel_total : 50549 time to create 1 rle with old method : 0.05937838554382324 length of segment : 462 time for calcul the mask position with numpy : 0.0017573833465576172 nb_pixel_total : 66305 time to create 1 rle with old method : 0.07853555679321289 length of segment : 336 time for calcul the mask position with numpy : 0.0030944347381591797 nb_pixel_total : 150269 time to create 1 rle with new method : 0.008905649185180664 length of segment : 595 time for calcul the mask position with numpy : 0.020766019821166992 nb_pixel_total : 169181 time to create 1 rle with new method : 0.01203608512878418 length of segment : 399 time for calcul the mask position with numpy : 0.029470443725585938 nb_pixel_total : 1256989 time to create 1 rle with new method : 0.21837139129638672 length of segment : 1538 time for calcul the mask position with numpy : 0.02048015594482422 nb_pixel_total : 713070 time to create 1 rle with new method : 0.07706260681152344 length of segment : 1028 time for calcul the mask position with numpy : 0.0033376216888427734 nb_pixel_total : 89026 time to create 1 rle with old method : 0.10419416427612305 length of segment : 309 time for calcul the mask position with numpy : 0.06260490417480469 nb_pixel_total : 984416 time to create 1 rle with new method : 0.1425173282623291 length of segment : 1542 time for calcul the mask position with numpy : 0.005266427993774414 nb_pixel_total : 36387 time to create 1 rle with old method : 0.04497981071472168 length of segment : 240 time for calcul the mask position with numpy : 0.03425335884094238 nb_pixel_total : 110718 time to create 1 rle with old method : 0.13962483406066895 length of segment : 502 time for calcul the mask position with numpy : 0.006471157073974609 nb_pixel_total : 116319 time to create 1 rle with old method : 0.15617680549621582 length of segment : 548 time for calcul the mask position with numpy : 0.001173257827758789 nb_pixel_total : 31248 time to create 1 rle with old method : 0.037256717681884766 length of segment : 150 time for calcul the mask position with numpy : 0.3188614845275879 nb_pixel_total : 1976723 time to create 1 rle with new method : 0.35390424728393555 length of segment : 1847 time for calcul the mask position with numpy : 0.0009298324584960938 nb_pixel_total : 35137 time to create 1 rle with old method : 0.0478518009185791 length of segment : 250 time for calcul the mask position with numpy : 0.0215756893157959 nb_pixel_total : 108685 time to create 1 rle with old method : 0.13337135314941406 length of segment : 495 time for calcul the mask position with numpy : 0.0011856555938720703 nb_pixel_total : 39179 time to create 1 rle with old method : 0.049541473388671875 length of segment : 270 time for calcul the mask position with numpy : 0.008394241333007812 nb_pixel_total : 169377 time to create 1 rle with new method : 0.008819341659545898 length of segment : 481 time for calcul the mask position with numpy : 0.0024225711822509766 nb_pixel_total : 102200 time to create 1 rle with old method : 0.12854266166687012 length of segment : 439 time for calcul the mask position with numpy : 0.13753485679626465 nb_pixel_total : 801908 time to create 1 rle with new method : 0.2555077075958252 length of segment : 1105 time for calcul the mask position with numpy : 0.0007586479187011719 nb_pixel_total : 31551 time to create 1 rle with old method : 0.038054704666137695 length of segment : 168 time for calcul the mask position with numpy : 0.0031664371490478516 nb_pixel_total : 147478 time to create 1 rle with old method : 0.17826199531555176 length of segment : 386 time for calcul the mask position with numpy : 0.0025177001953125 nb_pixel_total : 99898 time to create 1 rle with old method : 0.11739706993103027 length of segment : 463 time for calcul the mask position with numpy : 0.0039844512939453125 nb_pixel_total : 117403 time to create 1 rle with old method : 0.13706707954406738 length of segment : 475 time for calcul the mask position with numpy : 0.001588582992553711 nb_pixel_total : 60582 time to create 1 rle with old method : 0.09493613243103027 length of segment : 306 time for calcul the mask position with numpy : 0.0005702972412109375 nb_pixel_total : 27564 time to create 1 rle with old method : 0.03501272201538086 length of segment : 259 time for calcul the mask position with numpy : 0.0006189346313476562 nb_pixel_total : 14684 time to create 1 rle with old method : 0.019443035125732422 length of segment : 230 time for calcul the mask position with numpy : 0.017362594604492188 nb_pixel_total : 278657 time to create 1 rle with new method : 0.023954153060913086 length of segment : 1253 time for calcul the mask position with numpy : 0.02225518226623535 nb_pixel_total : 168205 time to create 1 rle with new method : 0.010582685470581055 length of segment : 425 time for calcul the mask position with numpy : 0.0022156238555908203 nb_pixel_total : 43746 time to create 1 rle with old method : 0.05221295356750488 length of segment : 806 time for calcul the mask position with numpy : 0.019218921661376953 nb_pixel_total : 340918 time to create 1 rle with new method : 0.022703886032104492 length of segment : 1126 time for calcul the mask position with numpy : 0.003443479537963867 nb_pixel_total : 77490 time to create 1 rle with old method : 0.09904837608337402 length of segment : 502 time for calcul the mask position with numpy : 0.003852367401123047 nb_pixel_total : 43142 time to create 1 rle with old method : 0.0536801815032959 length of segment : 483 time for calcul the mask position with numpy : 0.01092219352722168 nb_pixel_total : 132103 time to create 1 rle with old method : 0.15622520446777344 length of segment : 286 time for calcul the mask position with numpy : 0.004093170166015625 nb_pixel_total : 75942 time to create 1 rle with old method : 0.09110045433044434 length of segment : 291 time for calcul the mask position with numpy : 0.029980897903442383 nb_pixel_total : 483489 time to create 1 rle with new method : 0.024759292602539062 length of segment : 693 time for calcul the mask position with numpy : 0.0005905628204345703 nb_pixel_total : 23880 time to create 1 rle with old method : 0.028195619583129883 length of segment : 285 time for calcul the mask position with numpy : 0.0003323554992675781 nb_pixel_total : 13180 time to create 1 rle with old method : 0.016985177993774414 length of segment : 149 time for calcul the mask position with numpy : 0.016008853912353516 nb_pixel_total : 574841 time to create 1 rle with new method : 0.039786577224731445 length of segment : 888 time for calcul the mask position with numpy : 0.0003771781921386719 nb_pixel_total : 11075 time to create 1 rle with old method : 0.013174057006835938 length of segment : 141 time for calcul the mask position with numpy : 0.0013554096221923828 nb_pixel_total : 61857 time to create 1 rle with old method : 0.07322883605957031 length of segment : 364 time for calcul the mask position with numpy : 0.0015039443969726562 nb_pixel_total : 30986 time to create 1 rle with old method : 0.0373225212097168 length of segment : 257 time for calcul the mask position with numpy : 0.006211757659912109 nb_pixel_total : 80786 time to create 1 rle with old method : 0.09772133827209473 length of segment : 389 time for calcul the mask position with numpy : 0.0012998580932617188 nb_pixel_total : 42053 time to create 1 rle with old method : 0.04977750778198242 length of segment : 279 time for calcul the mask position with numpy : 0.0018155574798583984 nb_pixel_total : 51701 time to create 1 rle with old method : 0.06135702133178711 length of segment : 533 time for calcul the mask position with numpy : 0.007905960083007812 nb_pixel_total : 184129 time to create 1 rle with new method : 0.020441532135009766 length of segment : 560 time for calcul the mask position with numpy : 0.0037508010864257812 nb_pixel_total : 109611 time to create 1 rle with old method : 0.1343989372253418 length of segment : 1352 time for calcul the mask position with numpy : 0.0006978511810302734 nb_pixel_total : 34195 time to create 1 rle with old method : 0.04704475402832031 length of segment : 230 time for calcul the mask position with numpy : 0.003117084503173828 nb_pixel_total : 70142 time to create 1 rle with old method : 0.09273743629455566 length of segment : 421 time for calcul the mask position with numpy : 0.04267573356628418 nb_pixel_total : 541373 time to create 1 rle with new method : 0.25907111167907715 length of segment : 1371 time for calcul the mask position with numpy : 0.003260374069213867 nb_pixel_total : 64462 time to create 1 rle with old method : 0.0768129825592041 length of segment : 328 time for calcul the mask position with numpy : 0.0016067028045654297 nb_pixel_total : 80375 time to create 1 rle with old method : 0.1026158332824707 length of segment : 333 time for calcul the mask position with numpy : 0.002141714096069336 nb_pixel_total : 85979 time to create 1 rle with old method : 0.10324931144714355 length of segment : 344 time for calcul the mask position with numpy : 0.0018761157989501953 nb_pixel_total : 34006 time to create 1 rle with old method : 0.040604352951049805 length of segment : 387 time for calcul the mask position with numpy : 0.004291057586669922 nb_pixel_total : 209963 time to create 1 rle with new method : 0.012884378433227539 length of segment : 397 time for calcul the mask position with numpy : 0.0012638568878173828 nb_pixel_total : 25794 time to create 1 rle with old method : 0.030907869338989258 length of segment : 252 time for calcul the mask position with numpy : 0.009025812149047852 nb_pixel_total : 134731 time to create 1 rle with old method : 0.15978670120239258 length of segment : 532 time for calcul the mask position with numpy : 0.034300804138183594 nb_pixel_total : 359571 time to create 1 rle with new method : 0.019770383834838867 length of segment : 866 time for calcul the mask position with numpy : 0.0012919902801513672 nb_pixel_total : 61145 time to create 1 rle with old method : 0.07196497917175293 length of segment : 219 time for calcul the mask position with numpy : 0.013287067413330078 nb_pixel_total : 305603 time to create 1 rle with new method : 0.01740574836730957 length of segment : 675 time for calcul the mask position with numpy : 0.0018496513366699219 nb_pixel_total : 81456 time to create 1 rle with old method : 0.11744475364685059 length of segment : 771 time for calcul the mask position with numpy : 0.009654760360717773 nb_pixel_total : 471718 time to create 1 rle with new method : 0.02782154083251953 length of segment : 1068 time for calcul the mask position with numpy : 0.003399372100830078 nb_pixel_total : 177309 time to create 1 rle with new method : 0.009493589401245117 length of segment : 698 time for calcul the mask position with numpy : 0.0025959014892578125 nb_pixel_total : 84517 time to create 1 rle with old method : 0.10102438926696777 length of segment : 397 time for calcul the mask position with numpy : 0.002689838409423828 nb_pixel_total : 75432 time to create 1 rle with old method : 0.09097814559936523 length of segment : 530 time for calcul the mask position with numpy : 0.02864217758178711 nb_pixel_total : 794805 time to create 1 rle with new method : 0.2017374038696289 length of segment : 1271 time for calcul the mask position with numpy : 0.04899191856384277 nb_pixel_total : 699969 time to create 1 rle with new method : 0.27078676223754883 length of segment : 1826 time for calcul the mask position with numpy : 0.0015425682067871094 nb_pixel_total : 34870 time to create 1 rle with old method : 0.04396414756774902 length of segment : 162 time for calcul the mask position with numpy : 0.00548863410949707 nb_pixel_total : 149665 time to create 1 rle with old method : 0.1755530834197998 length of segment : 662 time for calcul the mask position with numpy : 0.0022296905517578125 nb_pixel_total : 41690 time to create 1 rle with old method : 0.04936790466308594 length of segment : 265 time for calcul the mask position with numpy : 0.13905835151672363 nb_pixel_total : 2036968 time to create 1 rle with new method : 0.4317929744720459 length of segment : 2100 time for calcul the mask position with numpy : 0.02208232879638672 nb_pixel_total : 288417 time to create 1 rle with new method : 0.06140565872192383 length of segment : 935 time for calcul the mask position with numpy : 0.001089334487915039 nb_pixel_total : 15471 time to create 1 rle with old method : 0.021651029586791992 length of segment : 173 time for calcul the mask position with numpy : 0.005109310150146484 nb_pixel_total : 180265 time to create 1 rle with new method : 0.011056661605834961 length of segment : 477 time for calcul the mask position with numpy : 0.001493215560913086 nb_pixel_total : 30045 time to create 1 rle with old method : 0.03630256652832031 length of segment : 358 time for calcul the mask position with numpy : 0.004135608673095703 nb_pixel_total : 120350 time to create 1 rle with old method : 0.14739489555358887 length of segment : 365 time for calcul the mask position with numpy : 0.0011053085327148438 nb_pixel_total : 28200 time to create 1 rle with old method : 0.034172773361206055 length of segment : 133 time for calcul the mask position with numpy : 0.0031778812408447266 nb_pixel_total : 39665 time to create 1 rle with old method : 0.05939054489135742 length of segment : 181 time for calcul the mask position with numpy : 0.004720449447631836 nb_pixel_total : 183468 time to create 1 rle with new method : 0.014607667922973633 length of segment : 609 time for calcul the mask position with numpy : 0.0009965896606445312 nb_pixel_total : 28947 time to create 1 rle with old method : 0.034970760345458984 length of segment : 291 time for calcul the mask position with numpy : 0.021605491638183594 nb_pixel_total : 449519 time to create 1 rle with new method : 0.12488460540771484 length of segment : 1161 time for calcul the mask position with numpy : 0.0011591911315917969 nb_pixel_total : 42786 time to create 1 rle with old method : 0.05328631401062012 length of segment : 249 time for calcul the mask position with numpy : 0.09968852996826172 nb_pixel_total : 2227449 time to create 1 rle with new method : 0.587252140045166 length of segment : 1986 time for calcul the mask position with numpy : 0.0029287338256835938 nb_pixel_total : 119229 time to create 1 rle with old method : 0.14019465446472168 length of segment : 432 time for calcul the mask position with numpy : 0.003789186477661133 nb_pixel_total : 175085 time to create 1 rle with new method : 0.014168262481689453 length of segment : 525 time for calcul the mask position with numpy : 0.015837430953979492 nb_pixel_total : 230897 time to create 1 rle with new method : 0.037470102310180664 length of segment : 1108 time for calcul the mask position with numpy : 0.0008287429809570312 nb_pixel_total : 19315 time to create 1 rle with old method : 0.023302316665649414 length of segment : 349 time for calcul the mask position with numpy : 0.0050547122955322266 nb_pixel_total : 201445 time to create 1 rle with new method : 0.016488075256347656 length of segment : 607 time for calcul the mask position with numpy : 0.013432502746582031 nb_pixel_total : 697682 time to create 1 rle with new method : 0.03175783157348633 length of segment : 1048 time for calcul the mask position with numpy : 0.004731655120849609 nb_pixel_total : 186547 time to create 1 rle with new method : 0.014206647872924805 length of segment : 553 time for calcul the mask position with numpy : 0.0010416507720947266 nb_pixel_total : 41803 time to create 1 rle with old method : 0.0646965503692627 length of segment : 327 time for calcul the mask position with numpy : 0.01478266716003418 nb_pixel_total : 390605 time to create 1 rle with new method : 0.03371691703796387 length of segment : 950 time for calcul the mask position with numpy : 0.040374040603637695 nb_pixel_total : 1881003 time to create 1 rle with new method : 0.342726469039917 length of segment : 1664 time for calcul the mask position with numpy : 0.003622293472290039 nb_pixel_total : 159230 time to create 1 rle with new method : 0.009988784790039062 length of segment : 617 time for calcul the mask position with numpy : 0.02799367904663086 nb_pixel_total : 677559 time to create 1 rle with new method : 0.05009961128234863 length of segment : 1056 time for calcul the mask position with numpy : 0.0020058155059814453 nb_pixel_total : 78546 time to create 1 rle with old method : 0.09596490859985352 length of segment : 442 time for calcul the mask position with numpy : 0.04916524887084961 nb_pixel_total : 1980012 time to create 1 rle with new method : 0.3390688896179199 length of segment : 1635 time for calcul the mask position with numpy : 0.0016646385192871094 nb_pixel_total : 72969 time to create 1 rle with old method : 0.09179067611694336 length of segment : 399 time for calcul the mask position with numpy : 0.0031430721282958984 nb_pixel_total : 133783 time to create 1 rle with old method : 0.1984264850616455 length of segment : 492 time for calcul the mask position with numpy : 0.0035715103149414062 nb_pixel_total : 56878 time to create 1 rle with old method : 0.07185840606689453 length of segment : 246 time for calcul the mask position with numpy : 0.003637075424194336 nb_pixel_total : 186219 time to create 1 rle with new method : 0.010598897933959961 length of segment : 416 time for calcul the mask position with numpy : 0.0005261898040771484 nb_pixel_total : 30251 time to create 1 rle with old method : 0.03958320617675781 length of segment : 288 time for calcul the mask position with numpy : 0.0025358200073242188 nb_pixel_total : 108353 time to create 1 rle with old method : 0.13631010055541992 length of segment : 347 time for calcul the mask position with numpy : 0.0024895668029785156 nb_pixel_total : 124965 time to create 1 rle with old method : 0.15280365943908691 length of segment : 373 time for calcul the mask position with numpy : 0.03168630599975586 nb_pixel_total : 1500924 time to create 1 rle with new method : 0.10319638252258301 length of segment : 1234 time for calcul the mask position with numpy : 0.0023529529571533203 nb_pixel_total : 129371 time to create 1 rle with old method : 0.15847086906433105 length of segment : 286 time for calcul the mask position with numpy : 0.0009162425994873047 nb_pixel_total : 36233 time to create 1 rle with old method : 0.042430877685546875 length of segment : 381 time for calcul the mask position with numpy : 0.0119781494140625 nb_pixel_total : 603334 time to create 1 rle with new method : 0.07404398918151855 length of segment : 818 time for calcul the mask position with numpy : 0.003139019012451172 nb_pixel_total : 61764 time to create 1 rle with old method : 0.10027074813842773 length of segment : 192 time for calcul the mask position with numpy : 0.0008213520050048828 nb_pixel_total : 28309 time to create 1 rle with old method : 0.03482937812805176 length of segment : 153 time for calcul the mask position with numpy : 0.04050612449645996 nb_pixel_total : 1292250 time to create 1 rle with new method : 0.22447538375854492 length of segment : 1759 time for calcul the mask position with numpy : 0.013333320617675781 nb_pixel_total : 592141 time to create 1 rle with new method : 0.05641746520996094 length of segment : 958 time for calcul the mask position with numpy : 0.0021593570709228516 nb_pixel_total : 101689 time to create 1 rle with old method : 0.13094019889831543 length of segment : 375 time for calcul the mask position with numpy : 0.05032753944396973 nb_pixel_total : 1976657 time to create 1 rle with new method : 0.3603842258453369 length of segment : 1824 time for calcul the mask position with numpy : 0.0024509429931640625 nb_pixel_total : 75557 time to create 1 rle with old method : 0.09135890007019043 length of segment : 178 time for calcul the mask position with numpy : 0.0024864673614501953 nb_pixel_total : 119230 time to create 1 rle with old method : 0.14002060890197754 length of segment : 472 time for calcul the mask position with numpy : 0.005974769592285156 nb_pixel_total : 296601 time to create 1 rle with new method : 0.018332719802856445 length of segment : 736 time for calcul the mask position with numpy : 0.007132291793823242 nb_pixel_total : 351159 time to create 1 rle with new method : 0.019415855407714844 length of segment : 939 time for calcul the mask position with numpy : 0.01755356788635254 nb_pixel_total : 867448 time to create 1 rle with new method : 0.0987083911895752 length of segment : 1203 time for calcul the mask position with numpy : 0.006167411804199219 nb_pixel_total : 326900 time to create 1 rle with new method : 0.015206575393676758 length of segment : 753 time for calcul the mask position with numpy : 0.0038902759552001953 nb_pixel_total : 175552 time to create 1 rle with new method : 0.01214909553527832 length of segment : 550 time for calcul the mask position with numpy : 0.014872074127197266 nb_pixel_total : 535439 time to create 1 rle with new method : 0.07572484016418457 length of segment : 961 time for calcul the mask position with numpy : 0.0016083717346191406 nb_pixel_total : 89696 time to create 1 rle with old method : 0.10823750495910645 length of segment : 428 time for calcul the mask position with numpy : 0.009940385818481445 nb_pixel_total : 575065 time to create 1 rle with new method : 0.022649049758911133 length of segment : 779 time for calcul the mask position with numpy : 0.004990816116333008 nb_pixel_total : 312615 time to create 1 rle with new method : 0.012500762939453125 length of segment : 840 time for calcul the mask position with numpy : 0.005683422088623047 nb_pixel_total : 306378 time to create 1 rle with new method : 0.016028881072998047 length of segment : 748 time for calcul the mask position with numpy : 0.0016880035400390625 nb_pixel_total : 83907 time to create 1 rle with old method : 0.09912443161010742 length of segment : 433 time for calcul the mask position with numpy : 0.03788185119628906 nb_pixel_total : 2193047 time to create 1 rle with new method : 0.6040902137756348 length of segment : 1983 time for calcul the mask position with numpy : 0.004238128662109375 nb_pixel_total : 137447 time to create 1 rle with old method : 0.1645979881286621 length of segment : 388 time for calcul the mask position with numpy : 0.0070035457611083984 nb_pixel_total : 376866 time to create 1 rle with new method : 0.018296003341674805 length of segment : 600 time for calcul the mask position with numpy : 0.0576932430267334 nb_pixel_total : 2242342 time to create 1 rle with new method : 0.6318540573120117 length of segment : 3566 time for calcul the mask position with numpy : 0.0021517276763916016 nb_pixel_total : 111527 time to create 1 rle with old method : 0.16555261611938477 length of segment : 458 time for calcul the mask position with numpy : 0.04095578193664551 nb_pixel_total : 2309001 time to create 1 rle with new method : 0.19931912422180176 length of segment : 2206 time for calcul the mask position with numpy : 0.2554636001586914 nb_pixel_total : 3483719 time to create 1 rle with new method : 0.5841314792633057 length of segment : 2726 time for calcul the mask position with numpy : 0.0017483234405517578 nb_pixel_total : 64396 time to create 1 rle with old method : 0.08801555633544922 length of segment : 532 time for calcul the mask position with numpy : 0.0013175010681152344 nb_pixel_total : 63835 time to create 1 rle with old method : 0.07223248481750488 length of segment : 526 time for calcul the mask position with numpy : 0.0021898746490478516 nb_pixel_total : 124432 time to create 1 rle with old method : 0.140791654586792 length of segment : 602 time for calcul the mask position with numpy : 0.002413034439086914 nb_pixel_total : 115312 time to create 1 rle with old method : 0.1333627700805664 length of segment : 466 time for calcul the mask position with numpy : 0.040625572204589844 nb_pixel_total : 1193884 time to create 1 rle with new method : 0.7147393226623535 length of segment : 2009 time for calcul the mask position with numpy : 0.0007843971252441406 nb_pixel_total : 41835 time to create 1 rle with old method : 0.04935455322265625 length of segment : 194 time for calcul the mask position with numpy : 0.0064885616302490234 nb_pixel_total : 394356 time to create 1 rle with new method : 0.014390945434570312 length of segment : 727 time for calcul the mask position with numpy : 0.0035295486450195312 nb_pixel_total : 237514 time to create 1 rle with new method : 0.008427619934082031 length of segment : 298 time for calcul the mask position with numpy : 0.0004374980926513672 nb_pixel_total : 17283 time to create 1 rle with old method : 0.020276308059692383 length of segment : 160 time for calcul the mask position with numpy : 0.0027375221252441406 nb_pixel_total : 216191 time to create 1 rle with new method : 0.006909608840942383 length of segment : 285 time for calcul the mask position with numpy : 0.004232883453369141 nb_pixel_total : 255059 time to create 1 rle with new method : 0.011444568634033203 length of segment : 782 time for calcul the mask position with numpy : 0.0007901191711425781 nb_pixel_total : 42276 time to create 1 rle with old method : 0.05045437812805176 length of segment : 391 time for calcul the mask position with numpy : 0.004079103469848633 nb_pixel_total : 239395 time to create 1 rle with new method : 0.011113643646240234 length of segment : 562 time for calcul the mask position with numpy : 0.0014908313751220703 nb_pixel_total : 50019 time to create 1 rle with old method : 0.0600430965423584 length of segment : 349 time for calcul the mask position with numpy : 0.0036182403564453125 nb_pixel_total : 141472 time to create 1 rle with old method : 0.18848752975463867 length of segment : 339 time for calcul the mask position with numpy : 0.012425661087036133 nb_pixel_total : 649010 time to create 1 rle with new method : 0.023879051208496094 length of segment : 707 time for calcul the mask position with numpy : 0.000461578369140625 nb_pixel_total : 20782 time to create 1 rle with old method : 0.026155948638916016 length of segment : 75 time for calcul the mask position with numpy : 0.0011165142059326172 nb_pixel_total : 72945 time to create 1 rle with old method : 0.08690142631530762 length of segment : 292 time for calcul the mask position with numpy : 0.0009834766387939453 nb_pixel_total : 65967 time to create 1 rle with old method : 0.0818486213684082 length of segment : 286 time for calcul the mask position with numpy : 0.012591838836669922 nb_pixel_total : 211867 time to create 1 rle with new method : 0.030669212341308594 length of segment : 646 time for calcul the mask position with numpy : 0.0018277168273925781 nb_pixel_total : 111393 time to create 1 rle with old method : 0.1336965560913086 length of segment : 388 time for calcul the mask position with numpy : 0.002468585968017578 nb_pixel_total : 124496 time to create 1 rle with old method : 0.1463756561279297 length of segment : 350 time for calcul the mask position with numpy : 0.0011310577392578125 nb_pixel_total : 65927 time to create 1 rle with old method : 0.07860994338989258 length of segment : 282 time for calcul the mask position with numpy : 0.0012004375457763672 nb_pixel_total : 61860 time to create 1 rle with old method : 0.0742952823638916 length of segment : 283 time spent for convertir_results : 94.07924103736877 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 405 chid ids of type : 4854 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 258.00357246398926 time spend to save output : 0.24563884735107422 total time spend for step 2 : 258.24921131134033 step3:blur_detection Tue Apr 1 02:07:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: variance laplacian (4160, 3120) 142.96850810668928 (4160, 3120) 1834.5902026211782 (4160, 3120) 1576.010065770194 (4160, 3120) 2209.5831355892365 (4160, 3120) 628.4168729001226 (4160, 3120) 1764.3295436377416 (4160, 3120) 118.29706638530128 (4160, 3120) 1376.6447892664648 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 8 time used for this insertion : 0.015930652618408203 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 8 time used for this insertion : 0.016326189041137695 save missing photos in datou_result : time spend for datou_step_exec : 4.0281407833099365 time spend to save output : 0.03748679161071777 total time spend for step 3 : 4.065627574920654 step4:brightness Tue Apr 1 02:07:25 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1743465692_2339854_1349036556_23db2def19ce09094a9e8dab92e4e8f8.jpg treat image : temp/1743465692_2339854_1349036552_ec5096a3cb0bfb36f27de0eccc578e6e.jpg treat image : temp/1743465692_2339854_1349036517_d583a4a3bab02d6d9512d5c17a3abe78.jpg treat image : temp/1743465692_2339854_1349036515_83e6dfc5b7b93327e773f0447324d069.jpg treat image : temp/1743465692_2339854_1349036509_e89669a90d2195488097c18c9ea44254.jpg treat image : temp/1743465692_2339854_1349036504_e0c2e57b5279ae3738d54a50c83bd6c5.jpg treat image : temp/1743465692_2339854_1349036502_88fd0a91ced747753a699aae83a83639.jpg treat image : temp/1743465692_2339854_1349036500_2b017a4ed37108a818b7bc7c44bcf49a.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 8 time used for this insertion : 0.013631343841552734 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 8 time used for this insertion : 0.013269901275634766 save missing photos in datou_result : time spend for datou_step_exec : 15.272021055221558 time spend to save output : 0.032753944396972656 total time spend for step 4 : 15.30477499961853 step5:rle_unique_nms_with_priority Tue Apr 1 02:07:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 405 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 22 nb_hashtags : 8 time to prepare the origin masks : 48.97024464607239 time for calcul the mask position with numpy : 0.1167287826538086 nb_pixel_total : 3039158 time to create 1 rle with new method : 2.997117519378662 time for calcul the mask position with numpy : 0.07700490951538086 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002472400665283203 time for calcul the mask position with numpy : 0.07486701011657715 nb_pixel_total : 820 time to create 1 rle with old method : 0.0011625289916992188 time for calcul the mask position with numpy : 0.10443925857543945 nb_pixel_total : 1694550 time to create 1 rle with new method : 1.5429296493530273 time for calcul the mask position with numpy : 0.0714731216430664 nb_pixel_total : 18768 time to create 1 rle with old method : 0.02262139320373535 time for calcul the mask position with numpy : 0.07151675224304199 nb_pixel_total : 158424 time to create 1 rle with new method : 1.4302761554718018 time for calcul the mask position with numpy : 0.07837796211242676 nb_pixel_total : 1127960 time to create 1 rle with new method : 1.2072889804840088 time for calcul the mask position with numpy : 0.07381987571716309 nb_pixel_total : 311940 time to create 1 rle with new method : 1.5207648277282715 time for calcul the mask position with numpy : 0.07210254669189453 nb_pixel_total : 8614 time to create 1 rle with old method : 0.010939359664916992 time for calcul the mask position with numpy : 0.07449555397033691 nb_pixel_total : 375648 time to create 1 rle with new method : 1.4747581481933594 time for calcul the mask position with numpy : 0.06625151634216309 nb_pixel_total : 94866 time to create 1 rle with old method : 0.11189627647399902 time for calcul the mask position with numpy : 0.07374858856201172 nb_pixel_total : 298227 time to create 1 rle with new method : 1.0837955474853516 time for calcul the mask position with numpy : 0.11012721061706543 nb_pixel_total : 2808106 time to create 1 rle with new method : 1.2170183658599854 time for calcul the mask position with numpy : 0.06385350227355957 nb_pixel_total : 23450 time to create 1 rle with old method : 0.026567697525024414 time for calcul the mask position with numpy : 0.06680846214294434 nb_pixel_total : 246299 time to create 1 rle with new method : 1.177025556564331 time for calcul the mask position with numpy : 0.0753321647644043 nb_pixel_total : 370026 time to create 1 rle with new method : 0.953176736831665 time for calcul the mask position with numpy : 0.06740593910217285 nb_pixel_total : 50439 time to create 1 rle with old method : 0.06528592109680176 time for calcul the mask position with numpy : 0.06836605072021484 nb_pixel_total : 24630 time to create 1 rle with old method : 0.0287930965423584 time for calcul the mask position with numpy : 0.07077336311340332 nb_pixel_total : 118770 time to create 1 rle with old method : 0.13972210884094238 time for calcul the mask position with numpy : 0.08417201042175293 nb_pixel_total : 896173 time to create 1 rle with new method : 1.0742261409759521 time for calcul the mask position with numpy : 0.08027935028076172 nb_pixel_total : 454149 time to create 1 rle with new method : 1.5275230407714844 time for calcul the mask position with numpy : 0.08251142501831055 nb_pixel_total : 137087 time to create 1 rle with old method : 0.16166234016418457 time for calcul the mask position with numpy : 0.07671642303466797 nb_pixel_total : 720921 time to create 1 rle with new method : 1.1738955974578857 create new chi : 21.431013584136963 time to delete rle : 0.02316880226135254 batch 1 Loaded 23 chid ids of type : 4855 Number RLEs to save : 38458 TO DO : save crop sub photo not yet done ! save time : 2.911545515060425 nb_obj : 74 nb_hashtags : 10 time to prepare the origin masks : 58.34866905212402 time for calcul the mask position with numpy : 0.32180047035217285 nb_pixel_total : 3338031 time to create 1 rle with new method : 1.7972745895385742 time for calcul the mask position with numpy : 0.05457735061645508 nb_pixel_total : 2099 time to create 1 rle with old method : 0.0027832984924316406 time for calcul the mask position with numpy : 0.056279897689819336 nb_pixel_total : 233301 time to create 1 rle with new method : 1.9831838607788086 time for calcul the mask position with numpy : 0.05413031578063965 nb_pixel_total : 58791 time to create 1 rle with old method : 0.0676271915435791 time for calcul the mask position with numpy : 0.054387569427490234 nb_pixel_total : 23475 time to create 1 rle with old method : 0.027454137802124023 time for calcul the mask position with numpy : 0.055103302001953125 nb_pixel_total : 195795 time to create 1 rle with new method : 1.5431606769561768 time for calcul the mask position with numpy : 0.05309939384460449 nb_pixel_total : 109417 time to create 1 rle with old method : 0.12795495986938477 time for calcul the mask position with numpy : 0.054121971130371094 nb_pixel_total : 242377 time to create 1 rle with new method : 1.7976653575897217 time for calcul the mask position with numpy : 0.051529884338378906 nb_pixel_total : 65083 time to create 1 rle with old method : 0.07132124900817871 time for calcul the mask position with numpy : 0.05148768424987793 nb_pixel_total : 122884 time to create 1 rle with old method : 0.13880515098571777 time for calcul the mask position with numpy : 0.053885698318481445 nb_pixel_total : 2277 time to create 1 rle with old method : 0.0025949478149414062 time for calcul the mask position with numpy : 0.0545194149017334 nb_pixel_total : 59318 time to create 1 rle with old method : 0.41248083114624023 time for calcul the mask position with numpy : 0.05426502227783203 nb_pixel_total : 17068 time to create 1 rle with old method : 0.0357511043548584 time for calcul the mask position with numpy : 0.07278227806091309 nb_pixel_total : 109199 time to create 1 rle with old method : 0.16724371910095215 time for calcul the mask position with numpy : 0.058974504470825195 nb_pixel_total : 88361 time to create 1 rle with old method : 0.10841202735900879 time for calcul the mask position with numpy : 0.05517745018005371 nb_pixel_total : 107968 time to create 1 rle with old method : 0.12752962112426758 time for calcul the mask position with numpy : 0.05315232276916504 nb_pixel_total : 12228 time to create 1 rle with old method : 0.014477729797363281 time for calcul the mask position with numpy : 0.05477571487426758 nb_pixel_total : 502358 time to create 1 rle with new method : 1.367769479751587 time for calcul the mask position with numpy : 0.06384730339050293 nb_pixel_total : 871951 time to create 1 rle with new method : 1.2767407894134521 time for calcul the mask position with numpy : 0.05381584167480469 nb_pixel_total : 22503 time to create 1 rle with old method : 0.026981115341186523 time for calcul the mask position with numpy : 0.05254054069519043 nb_pixel_total : 2782 time to create 1 rle with old method : 0.003206491470336914 time for calcul the mask position with numpy : 0.05308365821838379 nb_pixel_total : 7865 time to create 1 rle with old method : 0.009016275405883789 time for calcul the mask position with numpy : 0.05875706672668457 nb_pixel_total : 215292 time to create 1 rle with new method : 1.4166734218597412 time for calcul the mask position with numpy : 0.05425596237182617 nb_pixel_total : 53909 time to create 1 rle with old method : 0.08747172355651855 time for calcul the mask position with numpy : 0.05462193489074707 nb_pixel_total : 145148 time to create 1 rle with old method : 0.16868090629577637 time for calcul the mask position with numpy : 0.05618739128112793 nb_pixel_total : 40428 time to create 1 rle with old method : 0.0493316650390625 time for calcul the mask position with numpy : 0.054979562759399414 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003387928009033203 time for calcul the mask position with numpy : 0.059615135192871094 nb_pixel_total : 44628 time to create 1 rle with old method : 0.052602291107177734 time for calcul the mask position with numpy : 0.07484579086303711 nb_pixel_total : 517485 time to create 1 rle with new method : 1.3728582859039307 time for calcul the mask position with numpy : 0.0558774471282959 nb_pixel_total : 7571 time to create 1 rle with old method : 0.010927915573120117 time for calcul the mask position with numpy : 0.053388118743896484 nb_pixel_total : 107756 time to create 1 rle with old method : 0.12848377227783203 time for calcul the mask position with numpy : 0.0638279914855957 nb_pixel_total : 85179 time to create 1 rle with old method : 0.09998607635498047 time for calcul the mask position with numpy : 0.054096221923828125 nb_pixel_total : 6672 time to create 1 rle with old method : 0.008673429489135742 time for calcul the mask position with numpy : 0.05375409126281738 nb_pixel_total : 51354 time to create 1 rle with old method : 0.058484554290771484 time for calcul the mask position with numpy : 0.05495572090148926 nb_pixel_total : 10405 time to create 1 rle with old method : 0.012637615203857422 time for calcul the mask position with numpy : 0.05916094779968262 nb_pixel_total : 399962 time to create 1 rle with new method : 1.30080246925354 time for calcul the mask position with numpy : 0.05498480796813965 nb_pixel_total : 61479 time to create 1 rle with old method : 0.07303428649902344 time for calcul the mask position with numpy : 0.07910585403442383 nb_pixel_total : 659892 time to create 1 rle with new method : 1.9125409126281738 time for calcul the mask position with numpy : 0.05663943290710449 nb_pixel_total : 234904 time to create 1 rle with new method : 1.5227115154266357 time for calcul the mask position with numpy : 0.05428338050842285 nb_pixel_total : 11815 time to create 1 rle with old method : 0.015773773193359375 time for calcul the mask position with numpy : 0.055474281311035156 nb_pixel_total : 77262 time to create 1 rle with old method : 0.09247684478759766 time for calcul the mask position with numpy : 0.054634809494018555 nb_pixel_total : 74082 time to create 1 rle with old method : 0.08538961410522461 time for calcul the mask position with numpy : 0.06482076644897461 nb_pixel_total : 15431 time to create 1 rle with old method : 0.01971745491027832 time for calcul the mask position with numpy : 0.05691671371459961 nb_pixel_total : 274330 time to create 1 rle with new method : 1.208723545074463 time for calcul the mask position with numpy : 0.054827213287353516 nb_pixel_total : 37871 time to create 1 rle with old method : 0.044666290283203125 time for calcul the mask position with numpy : 0.055351972579956055 nb_pixel_total : 48074 time to create 1 rle with old method : 0.05547308921813965 time for calcul the mask position with numpy : 0.061338186264038086 nb_pixel_total : 315434 time to create 1 rle with new method : 1.4249939918518066 time for calcul the mask position with numpy : 0.05509543418884277 nb_pixel_total : 7545 time to create 1 rle with old method : 0.009396553039550781 time for calcul the mask position with numpy : 0.061315298080444336 nb_pixel_total : 58308 time to create 1 rle with old method : 0.06765031814575195 time for calcul the mask position with numpy : 0.054407596588134766 nb_pixel_total : 27043 time to create 1 rle with old method : 0.031543731689453125 time for calcul the mask position with numpy : 0.06081843376159668 nb_pixel_total : 585176 time to create 1 rle with new method : 1.453610897064209 time for calcul the mask position with numpy : 0.054654836654663086 nb_pixel_total : 69398 time to create 1 rle with old method : 0.08009004592895508 time for calcul the mask position with numpy : 0.05350828170776367 nb_pixel_total : 91033 time to create 1 rle with old method : 0.10084319114685059 time for calcul the mask position with numpy : 0.05299687385559082 nb_pixel_total : 60998 time to create 1 rle with old method : 0.0698094367980957 time for calcul the mask position with numpy : 0.05274820327758789 nb_pixel_total : 68175 time to create 1 rle with old method : 0.09805846214294434 time for calcul the mask position with numpy : 0.06170368194580078 nb_pixel_total : 321976 time to create 1 rle with new method : 1.067814588546753 time for calcul the mask position with numpy : 0.054569244384765625 nb_pixel_total : 12462 time to create 1 rle with old method : 0.016933202743530273 time for calcul the mask position with numpy : 0.06862759590148926 nb_pixel_total : 130440 time to create 1 rle with old method : 0.18786048889160156 time for calcul the mask position with numpy : 0.06148695945739746 nb_pixel_total : 249370 time to create 1 rle with new method : 1.2502191066741943 time for calcul the mask position with numpy : 0.05474042892456055 nb_pixel_total : 29333 time to create 1 rle with old method : 0.035825252532958984 time for calcul the mask position with numpy : 0.055886268615722656 nb_pixel_total : 83546 time to create 1 rle with old method : 0.09856009483337402 time for calcul the mask position with numpy : 0.08362722396850586 nb_pixel_total : 46402 time to create 1 rle with old method : 0.06309294700622559 time for calcul the mask position with numpy : 0.05373692512512207 nb_pixel_total : 32210 time to create 1 rle with old method : 0.037370920181274414 time for calcul the mask position with numpy : 0.054541587829589844 nb_pixel_total : 42666 time to create 1 rle with old method : 0.05011463165283203 time for calcul the mask position with numpy : 0.05759167671203613 nb_pixel_total : 135 time to create 1 rle with old method : 0.0005781650543212891 time for calcul the mask position with numpy : 0.06474089622497559 nb_pixel_total : 829590 time to create 1 rle with new method : 1.471182107925415 time for calcul the mask position with numpy : 0.05982398986816406 nb_pixel_total : 181717 time to create 1 rle with new method : 2.718745470046997 time for calcul the mask position with numpy : 0.05538010597229004 nb_pixel_total : 2190 time to create 1 rle with old method : 0.003566265106201172 time for calcul the mask position with numpy : 0.05502963066101074 nb_pixel_total : 25726 time to create 1 rle with old method : 0.031121492385864258 time for calcul the mask position with numpy : 0.05394792556762695 nb_pixel_total : 27752 time to create 1 rle with old method : 0.03282475471496582 time for calcul the mask position with numpy : 0.06273746490478516 nb_pixel_total : 164950 time to create 1 rle with new method : 1.2810628414154053 time for calcul the mask position with numpy : 0.055922508239746094 nb_pixel_total : 54506 time to create 1 rle with old method : 0.0660393238067627 time for calcul the mask position with numpy : 0.05548524856567383 nb_pixel_total : 78365 time to create 1 rle with old method : 0.10975241661071777 time for calcul the mask position with numpy : 0.05563092231750488 nb_pixel_total : 4545 time to create 1 rle with old method : 0.0059854984283447266 time for calcul the mask position with numpy : 0.05483531951904297 nb_pixel_total : 1957 time to create 1 rle with old method : 0.002544403076171875 create new chi : 38.30410051345825 time to delete rle : 0.011852025985717773 batch 1 Loaded 75 chid ids of type : 4855 Number RLEs to save : 59881 TO DO : save crop sub photo not yet done ! save time : 10.601721048355103 nb_obj : 54 nb_hashtags : 10 time to prepare the origin masks : 63.13916015625 time for calcul the mask position with numpy : 0.5837998390197754 nb_pixel_total : 5031657 time to create 1 rle with new method : 1.6702895164489746 time for calcul the mask position with numpy : 0.05451393127441406 nb_pixel_total : 65350 time to create 1 rle with old method : 0.07573676109313965 time for calcul the mask position with numpy : 0.05362272262573242 nb_pixel_total : 3355 time to create 1 rle with old method : 0.004314422607421875 time for calcul the mask position with numpy : 0.05374765396118164 nb_pixel_total : 1727 time to create 1 rle with old method : 0.0024712085723876953 time for calcul the mask position with numpy : 0.05531120300292969 nb_pixel_total : 122325 time to create 1 rle with old method : 0.14206671714782715 time for calcul the mask position with numpy : 0.05433154106140137 nb_pixel_total : 45312 time to create 1 rle with old method : 0.05283474922180176 time for calcul the mask position with numpy : 0.05583930015563965 nb_pixel_total : 42104 time to create 1 rle with old method : 0.04929184913635254 time for calcul the mask position with numpy : 0.05394577980041504 nb_pixel_total : 33097 time to create 1 rle with old method : 0.039475440979003906 time for calcul the mask position with numpy : 0.05343985557556152 nb_pixel_total : 153 time to create 1 rle with old method : 0.0003745555877685547 time for calcul the mask position with numpy : 0.07657027244567871 nb_pixel_total : 875505 time to create 1 rle with new method : 2.0490236282348633 time for calcul the mask position with numpy : 0.053559303283691406 nb_pixel_total : 7210 time to create 1 rle with old method : 0.012952089309692383 time for calcul the mask position with numpy : 0.06163763999938965 nb_pixel_total : 589169 time to create 1 rle with new method : 1.0752756595611572 time for calcul the mask position with numpy : 0.05570650100708008 nb_pixel_total : 86879 time to create 1 rle with old method : 0.1007542610168457 time for calcul the mask position with numpy : 0.05462646484375 nb_pixel_total : 58719 time to create 1 rle with old method : 0.0698099136352539 time for calcul the mask position with numpy : 0.05585503578186035 nb_pixel_total : 208989 time to create 1 rle with new method : 1.2718110084533691 time for calcul the mask position with numpy : 0.056272268295288086 nb_pixel_total : 207788 time to create 1 rle with new method : 1.2470626831054688 time for calcul the mask position with numpy : 0.054802656173706055 nb_pixel_total : 70898 time to create 1 rle with old method : 0.08484435081481934 time for calcul the mask position with numpy : 0.05429816246032715 nb_pixel_total : 15362 time to create 1 rle with old method : 0.01836538314819336 time for calcul the mask position with numpy : 0.05466723442077637 nb_pixel_total : 66364 time to create 1 rle with old method : 0.07782316207885742 time for calcul the mask position with numpy : 0.05625772476196289 nb_pixel_total : 332902 time to create 1 rle with new method : 1.3302497863769531 time for calcul the mask position with numpy : 0.055895090103149414 nb_pixel_total : 290122 time to create 1 rle with new method : 1.3798227310180664 time for calcul the mask position with numpy : 0.056099653244018555 nb_pixel_total : 160456 time to create 1 rle with new method : 1.2019705772399902 time for calcul the mask position with numpy : 0.0673067569732666 nb_pixel_total : 452379 time to create 1 rle with new method : 1.9538018703460693 time for calcul the mask position with numpy : 0.06328582763671875 nb_pixel_total : 57134 time to create 1 rle with old method : 0.06990194320678711 time for calcul the mask position with numpy : 0.05379462242126465 nb_pixel_total : 14978 time to create 1 rle with old method : 0.01712632179260254 time for calcul the mask position with numpy : 0.05891609191894531 nb_pixel_total : 8209 time to create 1 rle with old method : 0.009674787521362305 time for calcul the mask position with numpy : 0.05331873893737793 nb_pixel_total : 10492 time to create 1 rle with old method : 0.01258397102355957 time for calcul the mask position with numpy : 0.053203582763671875 nb_pixel_total : 14738 time to create 1 rle with old method : 0.01694512367248535 time for calcul the mask position with numpy : 0.05379533767700195 nb_pixel_total : 68399 time to create 1 rle with old method : 0.07620429992675781 time for calcul the mask position with numpy : 0.058684349060058594 nb_pixel_total : 440496 time to create 1 rle with new method : 1.1309077739715576 time for calcul the mask position with numpy : 0.05464601516723633 nb_pixel_total : 112096 time to create 1 rle with old method : 0.1280379295349121 time for calcul the mask position with numpy : 0.05573248863220215 nb_pixel_total : 17663 time to create 1 rle with old method : 0.02114701271057129 time for calcul the mask position with numpy : 0.05647754669189453 nb_pixel_total : 146397 time to create 1 rle with old method : 0.16935396194458008 time for calcul the mask position with numpy : 0.0560297966003418 nb_pixel_total : 128300 time to create 1 rle with old method : 0.17160511016845703 time for calcul the mask position with numpy : 0.054622650146484375 nb_pixel_total : 19046 time to create 1 rle with old method : 0.022188663482666016 time for calcul the mask position with numpy : 0.05716133117675781 nb_pixel_total : 206631 time to create 1 rle with new method : 1.056272029876709 time for calcul the mask position with numpy : 0.05583977699279785 nb_pixel_total : 92055 time to create 1 rle with old method : 0.10663461685180664 time for calcul the mask position with numpy : 0.0568997859954834 nb_pixel_total : 189469 time to create 1 rle with new method : 1.4058728218078613 time for calcul the mask position with numpy : 0.05690956115722656 nb_pixel_total : 82913 time to create 1 rle with old method : 0.09561800956726074 time for calcul the mask position with numpy : 0.054720163345336914 nb_pixel_total : 35597 time to create 1 rle with old method : 0.041182756423950195 time for calcul the mask position with numpy : 0.05487418174743652 nb_pixel_total : 3892 time to create 1 rle with old method : 0.004914045333862305 time for calcul the mask position with numpy : 0.07853841781616211 nb_pixel_total : 1215834 time to create 1 rle with new method : 0.9730026721954346 time for calcul the mask position with numpy : 0.05373835563659668 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0015900135040283203 time for calcul the mask position with numpy : 0.05389595031738281 nb_pixel_total : 6 time to create 1 rle with old method : 3.814697265625e-05 time for calcul the mask position with numpy : 0.06504344940185547 nb_pixel_total : 464413 time to create 1 rle with new method : 1.111818790435791 time for calcul the mask position with numpy : 0.0600583553314209 nb_pixel_total : 97437 time to create 1 rle with old method : 0.11477231979370117 time for calcul the mask position with numpy : 0.055178165435791016 nb_pixel_total : 8597 time to create 1 rle with old method : 0.010448455810546875 time for calcul the mask position with numpy : 0.05711984634399414 nb_pixel_total : 66739 time to create 1 rle with old method : 0.0788416862487793 time for calcul the mask position with numpy : 0.05956149101257324 nb_pixel_total : 213576 time to create 1 rle with new method : 1.2820777893066406 time for calcul the mask position with numpy : 0.05681800842285156 nb_pixel_total : 253396 time to create 1 rle with new method : 0.8762824535369873 time for calcul the mask position with numpy : 0.052910804748535156 nb_pixel_total : 9996 time to create 1 rle with old method : 0.011689901351928711 time for calcul the mask position with numpy : 0.0530848503112793 nb_pixel_total : 6312 time to create 1 rle with old method : 0.0073375701904296875 time for calcul the mask position with numpy : 0.0552065372467041 nb_pixel_total : 101439 time to create 1 rle with old method : 0.11627817153930664 time for calcul the mask position with numpy : 0.05379772186279297 nb_pixel_total : 71692 time to create 1 rle with old method : 0.0809030532836914 time for calcul the mask position with numpy : 0.053106069564819336 nb_pixel_total : 52173 time to create 1 rle with old method : 0.05810809135437012 create new chi : 27.771721839904785 time to delete rle : 0.0060727596282958984 batch 1 Loaded 55 chid ids of type : 4855 Number RLEs to save : 45755 TO DO : save crop sub photo not yet done ! save time : 16.402358293533325 nb_obj : 69 nb_hashtags : 10 time to prepare the origin masks : 60.541213274002075 time for calcul the mask position with numpy : 0.3739497661590576 nb_pixel_total : 3949648 time to create 1 rle with new method : 1.7392127513885498 time for calcul the mask position with numpy : 0.053208351135253906 nb_pixel_total : 36151 time to create 1 rle with old method : 0.040381669998168945 time for calcul the mask position with numpy : 0.05272173881530762 nb_pixel_total : 44657 time to create 1 rle with old method : 0.04934096336364746 time for calcul the mask position with numpy : 0.05644822120666504 nb_pixel_total : 373155 time to create 1 rle with new method : 1.0466856956481934 time for calcul the mask position with numpy : 0.05389118194580078 nb_pixel_total : 1965 time to create 1 rle with old method : 0.002535104751586914 time for calcul the mask position with numpy : 0.05408596992492676 nb_pixel_total : 34042 time to create 1 rle with old method : 0.04038429260253906 time for calcul the mask position with numpy : 0.05478549003601074 nb_pixel_total : 31495 time to create 1 rle with old method : 0.03694891929626465 time for calcul the mask position with numpy : 0.05423140525817871 nb_pixel_total : 39112 time to create 1 rle with old method : 0.04582357406616211 time for calcul the mask position with numpy : 0.062469482421875 nb_pixel_total : 78576 time to create 1 rle with old method : 0.09810376167297363 time for calcul the mask position with numpy : 0.06283450126647949 nb_pixel_total : 327479 time to create 1 rle with new method : 1.152345895767212 time for calcul the mask position with numpy : 0.05631518363952637 nb_pixel_total : 76211 time to create 1 rle with old method : 0.11875581741333008 time for calcul the mask position with numpy : 0.064666748046875 nb_pixel_total : 149035 time to create 1 rle with old method : 0.17362093925476074 time for calcul the mask position with numpy : 0.05632925033569336 nb_pixel_total : 27715 time to create 1 rle with old method : 0.03201723098754883 time for calcul the mask position with numpy : 0.055824995040893555 nb_pixel_total : 4204 time to create 1 rle with old method : 0.005016803741455078 time for calcul the mask position with numpy : 0.052550554275512695 nb_pixel_total : 24853 time to create 1 rle with old method : 0.027942895889282227 time for calcul the mask position with numpy : 0.05209851264953613 nb_pixel_total : 21710 time to create 1 rle with old method : 0.02397942543029785 time for calcul the mask position with numpy : 0.051863908767700195 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004405975341796875 time for calcul the mask position with numpy : 0.054160356521606445 nb_pixel_total : 32027 time to create 1 rle with old method : 0.0352327823638916 time for calcul the mask position with numpy : 0.0526273250579834 nb_pixel_total : 38050 time to create 1 rle with old method : 0.04343819618225098 time for calcul the mask position with numpy : 0.055210113525390625 nb_pixel_total : 163480 time to create 1 rle with new method : 1.6286096572875977 time for calcul the mask position with numpy : 0.056281089782714844 nb_pixel_total : 191660 time to create 1 rle with new method : 1.3117990493774414 time for calcul the mask position with numpy : 0.05423259735107422 nb_pixel_total : 1736 time to create 1 rle with old method : 0.0023298263549804688 time for calcul the mask position with numpy : 0.05303502082824707 nb_pixel_total : 4066 time to create 1 rle with old method : 0.0052204132080078125 time for calcul the mask position with numpy : 0.057737112045288086 nb_pixel_total : 146623 time to create 1 rle with old method : 0.16591119766235352 time for calcul the mask position with numpy : 0.06010603904724121 nb_pixel_total : 76723 time to create 1 rle with old method : 0.08931612968444824 time for calcul the mask position with numpy : 0.05646181106567383 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0016722679138183594 time for calcul the mask position with numpy : 0.05472683906555176 nb_pixel_total : 60066 time to create 1 rle with old method : 0.06864571571350098 time for calcul the mask position with numpy : 0.05730104446411133 nb_pixel_total : 313775 time to create 1 rle with new method : 1.3387036323547363 time for calcul the mask position with numpy : 0.07023334503173828 nb_pixel_total : 741896 time to create 1 rle with new method : 1.4737751483917236 time for calcul the mask position with numpy : 0.05572009086608887 nb_pixel_total : 68376 time to create 1 rle with old method : 0.0791158676147461 time for calcul the mask position with numpy : 0.054987192153930664 nb_pixel_total : 41137 time to create 1 rle with old method : 0.04712343215942383 time for calcul the mask position with numpy : 0.05632948875427246 nb_pixel_total : 20489 time to create 1 rle with old method : 0.023082494735717773 time for calcul the mask position with numpy : 0.053807735443115234 nb_pixel_total : 43404 time to create 1 rle with old method : 0.04975724220275879 time for calcul the mask position with numpy : 0.055695295333862305 nb_pixel_total : 210223 time to create 1 rle with new method : 1.9269719123840332 time for calcul the mask position with numpy : 0.05562448501586914 nb_pixel_total : 45347 time to create 1 rle with old method : 0.053531646728515625 time for calcul the mask position with numpy : 0.054380178451538086 nb_pixel_total : 12457 time to create 1 rle with old method : 0.014677286148071289 time for calcul the mask position with numpy : 0.05389213562011719 nb_pixel_total : 168755 time to create 1 rle with new method : 1.2307024002075195 time for calcul the mask position with numpy : 0.05710148811340332 nb_pixel_total : 261867 time to create 1 rle with new method : 1.853269100189209 time for calcul the mask position with numpy : 0.05565953254699707 nb_pixel_total : 95557 time to create 1 rle with old method : 0.10659956932067871 time for calcul the mask position with numpy : 0.052973031997680664 nb_pixel_total : 41913 time to create 1 rle with old method : 0.048372745513916016 time for calcul the mask position with numpy : 0.052832603454589844 nb_pixel_total : 27073 time to create 1 rle with old method : 0.031922340393066406 time for calcul the mask position with numpy : 0.055657386779785156 nb_pixel_total : 345133 time to create 1 rle with new method : 1.4644403457641602 time for calcul the mask position with numpy : 0.05313587188720703 nb_pixel_total : 15851 time to create 1 rle with old method : 0.017930984497070312 time for calcul the mask position with numpy : 0.053319692611694336 nb_pixel_total : 72315 time to create 1 rle with old method : 0.08081388473510742 time for calcul the mask position with numpy : 0.07603979110717773 nb_pixel_total : 1265578 time to create 1 rle with new method : 1.5218710899353027 time for calcul the mask position with numpy : 0.052922725677490234 nb_pixel_total : 144267 time to create 1 rle with old method : 0.16375970840454102 time for calcul the mask position with numpy : 0.0542752742767334 nb_pixel_total : 274068 time to create 1 rle with new method : 0.7742412090301514 time for calcul the mask position with numpy : 0.05424213409423828 nb_pixel_total : 65628 time to create 1 rle with old method : 0.07682251930236816 time for calcul the mask position with numpy : 0.05502915382385254 nb_pixel_total : 32565 time to create 1 rle with old method : 0.03819918632507324 time for calcul the mask position with numpy : 0.05420541763305664 nb_pixel_total : 9656 time to create 1 rle with old method : 0.01149749755859375 time for calcul the mask position with numpy : 0.055443525314331055 nb_pixel_total : 131594 time to create 1 rle with old method : 0.1721954345703125 time for calcul the mask position with numpy : 0.0540928840637207 nb_pixel_total : 222 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.05439329147338867 nb_pixel_total : 45218 time to create 1 rle with old method : 0.05274653434753418 time for calcul the mask position with numpy : 0.058205604553222656 nb_pixel_total : 347674 time to create 1 rle with new method : 1.7116317749023438 time for calcul the mask position with numpy : 0.062020063400268555 nb_pixel_total : 4445 time to create 1 rle with old method : 0.005698204040527344 time for calcul the mask position with numpy : 0.05826973915100098 nb_pixel_total : 283124 time to create 1 rle with new method : 1.3484101295471191 time for calcul the mask position with numpy : 0.05553388595581055 nb_pixel_total : 146247 time to create 1 rle with old method : 0.16636276245117188 time for calcul the mask position with numpy : 0.052983999252319336 nb_pixel_total : 117305 time to create 1 rle with old method : 0.13532423973083496 time for calcul the mask position with numpy : 0.054082393646240234 nb_pixel_total : 497 time to create 1 rle with old method : 0.001275777816772461 time for calcul the mask position with numpy : 0.05344676971435547 nb_pixel_total : 13936 time to create 1 rle with old method : 0.0157778263092041 time for calcul the mask position with numpy : 0.05261802673339844 nb_pixel_total : 25881 time to create 1 rle with old method : 0.02850651741027832 time for calcul the mask position with numpy : 0.052152156829833984 nb_pixel_total : 32137 time to create 1 rle with old method : 0.036229848861694336 time for calcul the mask position with numpy : 0.05194449424743652 nb_pixel_total : 11528 time to create 1 rle with old method : 0.0128326416015625 time for calcul the mask position with numpy : 0.06327009201049805 nb_pixel_total : 906860 time to create 1 rle with new method : 1.3862977027893066 time for calcul the mask position with numpy : 0.054630279541015625 nb_pixel_total : 129905 time to create 1 rle with old method : 0.1547696590423584 time for calcul the mask position with numpy : 0.052706241607666016 nb_pixel_total : 18239 time to create 1 rle with old method : 0.020829439163208008 time for calcul the mask position with numpy : 0.05610203742980957 nb_pixel_total : 120114 time to create 1 rle with old method : 0.14000654220581055 time for calcul the mask position with numpy : 0.05475211143493652 nb_pixel_total : 8593 time to create 1 rle with old method : 0.011095523834228516 time for calcul the mask position with numpy : 0.0575709342956543 nb_pixel_total : 332073 time to create 1 rle with new method : 1.5375826358795166 time for calcul the mask position with numpy : 0.05394554138183594 nb_pixel_total : 50437 time to create 1 rle with old method : 0.05730080604553223 create new chi : 32.54673099517822 time to delete rle : 0.006440877914428711 batch 1 Loaded 70 chid ids of type : 4855 Number RLEs to save : 56828 TO DO : save crop sub photo not yet done ! save time : 8.47937273979187 nb_obj : 52 nb_hashtags : 9 time to prepare the origin masks : 54.14664912223816 time for calcul the mask position with numpy : 0.36440587043762207 nb_pixel_total : 3274615 time to create 1 rle with new method : 1.3741092681884766 time for calcul the mask position with numpy : 0.05649971961975098 nb_pixel_total : 88827 time to create 1 rle with old method : 0.10413336753845215 time for calcul the mask position with numpy : 0.05620741844177246 nb_pixel_total : 22015 time to create 1 rle with old method : 0.02755427360534668 time for calcul the mask position with numpy : 0.05569291114807129 nb_pixel_total : 31205 time to create 1 rle with old method : 0.036656856536865234 time for calcul the mask position with numpy : 0.08364558219909668 nb_pixel_total : 394852 time to create 1 rle with new method : 1.189551830291748 time for calcul the mask position with numpy : 0.05713677406311035 nb_pixel_total : 69913 time to create 1 rle with old method : 0.10394859313964844 time for calcul the mask position with numpy : 0.05472564697265625 nb_pixel_total : 21467 time to create 1 rle with old method : 0.025405168533325195 time for calcul the mask position with numpy : 0.05608224868774414 nb_pixel_total : 80554 time to create 1 rle with old method : 0.09390807151794434 time for calcul the mask position with numpy : 0.05492448806762695 nb_pixel_total : 64402 time to create 1 rle with old method : 0.08705258369445801 time for calcul the mask position with numpy : 0.06138348579406738 nb_pixel_total : 13128 time to create 1 rle with old method : 0.015318632125854492 time for calcul the mask position with numpy : 0.05547785758972168 nb_pixel_total : 117113 time to create 1 rle with old method : 0.1411304473876953 time for calcul the mask position with numpy : 0.0630950927734375 nb_pixel_total : 30849 time to create 1 rle with old method : 0.0354619026184082 time for calcul the mask position with numpy : 0.05436563491821289 nb_pixel_total : 69290 time to create 1 rle with old method : 0.08017516136169434 time for calcul the mask position with numpy : 0.05701565742492676 nb_pixel_total : 131516 time to create 1 rle with old method : 0.15297269821166992 time for calcul the mask position with numpy : 0.05552053451538086 nb_pixel_total : 169133 time to create 1 rle with new method : 1.402435302734375 time for calcul the mask position with numpy : 0.15793967247009277 nb_pixel_total : 792829 time to create 1 rle with new method : 1.3822550773620605 time for calcul the mask position with numpy : 0.05683612823486328 nb_pixel_total : 17384 time to create 1 rle with old method : 0.028794288635253906 time for calcul the mask position with numpy : 0.06452679634094238 nb_pixel_total : 332606 time to create 1 rle with new method : 1.235295057296753 time for calcul the mask position with numpy : 0.0555877685546875 nb_pixel_total : 108417 time to create 1 rle with old method : 0.12369585037231445 time for calcul the mask position with numpy : 0.05466628074645996 nb_pixel_total : 36355 time to create 1 rle with old method : 0.05313563346862793 time for calcul the mask position with numpy : 0.05448603630065918 nb_pixel_total : 26949 time to create 1 rle with old method : 0.0312504768371582 time for calcul the mask position with numpy : 0.05462789535522461 nb_pixel_total : 14100 time to create 1 rle with old method : 0.01687335968017578 time for calcul the mask position with numpy : 0.11635494232177734 nb_pixel_total : 1876642 time to create 1 rle with new method : 1.18039870262146 time for calcul the mask position with numpy : 0.05419802665710449 nb_pixel_total : 37040 time to create 1 rle with old method : 0.043343305587768555 time for calcul the mask position with numpy : 0.05976390838623047 nb_pixel_total : 19347 time to create 1 rle with old method : 0.022492408752441406 time for calcul the mask position with numpy : 0.0578150749206543 nb_pixel_total : 1241 time to create 1 rle with old method : 0.00214385986328125 time for calcul the mask position with numpy : 0.058783769607543945 nb_pixel_total : 115566 time to create 1 rle with old method : 0.13926196098327637 time for calcul the mask position with numpy : 0.05905628204345703 nb_pixel_total : 8895 time to create 1 rle with old method : 0.01054692268371582 time for calcul the mask position with numpy : 0.053723812103271484 nb_pixel_total : 1596 time to create 1 rle with old method : 0.0021028518676757812 time for calcul the mask position with numpy : 0.060957908630371094 nb_pixel_total : 533073 time to create 1 rle with new method : 1.2609031200408936 time for calcul the mask position with numpy : 0.05494856834411621 nb_pixel_total : 110618 time to create 1 rle with old method : 0.12980103492736816 time for calcul the mask position with numpy : 0.06275296211242676 nb_pixel_total : 21065 time to create 1 rle with old method : 0.04327130317687988 time for calcul the mask position with numpy : 0.07796931266784668 nb_pixel_total : 982771 time to create 1 rle with new method : 1.4543564319610596 time for calcul the mask position with numpy : 0.05432701110839844 nb_pixel_total : 43066 time to create 1 rle with old method : 0.05026817321777344 time for calcul the mask position with numpy : 0.05398130416870117 nb_pixel_total : 31822 time to create 1 rle with old method : 0.037950754165649414 time for calcul the mask position with numpy : 0.06588244438171387 nb_pixel_total : 1266408 time to create 1 rle with new method : 1.38002610206604 time for calcul the mask position with numpy : 0.05572223663330078 nb_pixel_total : 140524 time to create 1 rle with old method : 0.17220783233642578 time for calcul the mask position with numpy : 0.06156659126281738 nb_pixel_total : 99351 time to create 1 rle with old method : 0.11702799797058105 time for calcul the mask position with numpy : 0.05506134033203125 nb_pixel_total : 101285 time to create 1 rle with old method : 0.12410211563110352 time for calcul the mask position with numpy : 0.10037350654602051 nb_pixel_total : 58709 time to create 1 rle with old method : 0.08432149887084961 time for calcul the mask position with numpy : 0.055651187896728516 nb_pixel_total : 11048 time to create 1 rle with old method : 0.017672300338745117 time for calcul the mask position with numpy : 0.07144856452941895 nb_pixel_total : 711633 time to create 1 rle with new method : 1.3217897415161133 time for calcul the mask position with numpy : 0.05455327033996582 nb_pixel_total : 79909 time to create 1 rle with old method : 0.09156608581542969 time for calcul the mask position with numpy : 0.0562283992767334 nb_pixel_total : 278459 time to create 1 rle with new method : 2.6225295066833496 time for calcul the mask position with numpy : 0.061112165451049805 nb_pixel_total : 293539 time to create 1 rle with new method : 1.6983094215393066 time for calcul the mask position with numpy : 0.07179737091064453 nb_pixel_total : 85 time to create 1 rle with old method : 0.00014448165893554688 time for calcul the mask position with numpy : 0.054434776306152344 nb_pixel_total : 2331 time to create 1 rle with old method : 0.0028984546661376953 time for calcul the mask position with numpy : 0.05503082275390625 nb_pixel_total : 22653 time to create 1 rle with old method : 0.02631211280822754 time for calcul the mask position with numpy : 0.06412529945373535 nb_pixel_total : 38849 time to create 1 rle with old method : 0.0832984447479248 time for calcul the mask position with numpy : 0.05658102035522461 nb_pixel_total : 116085 time to create 1 rle with old method : 0.15922284126281738 time for calcul the mask position with numpy : 0.07664847373962402 nb_pixel_total : 39744 time to create 1 rle with old method : 0.06458210945129395 time for calcul the mask position with numpy : 0.05384683609008789 nb_pixel_total : 1131 time to create 1 rle with old method : 0.0014586448669433594 time for calcul the mask position with numpy : 0.05483698844909668 nb_pixel_total : 27196 time to create 1 rle with old method : 0.03126716613769531 create new chi : 24.479971170425415 time to delete rle : 0.00754094123840332 batch 1 Loaded 53 chid ids of type : 4855 Number RLEs to save : 50592 TO DO : save crop sub photo not yet done ! save time : 6.483000755310059 nb_obj : 56 nb_hashtags : 11 time to prepare the origin masks : 55.390668630599976 time for calcul the mask position with numpy : 0.571533203125 nb_pixel_total : 2796248 time to create 1 rle with new method : 2.209902048110962 time for calcul the mask position with numpy : 0.05150461196899414 nb_pixel_total : 18128 time to create 1 rle with old method : 0.01984858512878418 time for calcul the mask position with numpy : 0.05190682411193848 nb_pixel_total : 27946 time to create 1 rle with old method : 0.03201770782470703 time for calcul the mask position with numpy : 0.05698442459106445 nb_pixel_total : 134334 time to create 1 rle with old method : 0.1535041332244873 time for calcul the mask position with numpy : 0.05531907081604004 nb_pixel_total : 39583 time to create 1 rle with old method : 0.04653739929199219 time for calcul the mask position with numpy : 0.05489182472229004 nb_pixel_total : 13223 time to create 1 rle with old method : 0.01590418815612793 time for calcul the mask position with numpy : 0.053984642028808594 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003204345703125 time for calcul the mask position with numpy : 0.0525813102722168 nb_pixel_total : 29819 time to create 1 rle with old method : 0.03348278999328613 time for calcul the mask position with numpy : 0.05516552925109863 nb_pixel_total : 182839 time to create 1 rle with new method : 2.213721990585327 time for calcul the mask position with numpy : 0.05163002014160156 nb_pixel_total : 1939 time to create 1 rle with old method : 0.0023527145385742188 time for calcul the mask position with numpy : 0.052146196365356445 nb_pixel_total : 34609 time to create 1 rle with old method : 0.039263248443603516 time for calcul the mask position with numpy : 0.0520787239074707 nb_pixel_total : 3050 time to create 1 rle with old method : 0.0037500858306884766 time for calcul the mask position with numpy : 0.05480623245239258 nb_pixel_total : 167806 time to create 1 rle with new method : 1.9870059490203857 time for calcul the mask position with numpy : 0.05258917808532715 nb_pixel_total : 1670 time to create 1 rle with old method : 0.0025169849395751953 time for calcul the mask position with numpy : 0.05664706230163574 nb_pixel_total : 288887 time to create 1 rle with new method : 2.0144448280334473 time for calcul the mask position with numpy : 0.05879330635070801 nb_pixel_total : 13415 time to create 1 rle with old method : 0.017071247100830078 time for calcul the mask position with numpy : 0.05370450019836426 nb_pixel_total : 6519 time to create 1 rle with old method : 0.0076389312744140625 time for calcul the mask position with numpy : 0.05580925941467285 nb_pixel_total : 200806 time to create 1 rle with new method : 1.725081205368042 time for calcul the mask position with numpy : 0.05374336242675781 nb_pixel_total : 7113 time to create 1 rle with old method : 0.008463621139526367 time for calcul the mask position with numpy : 0.06930661201477051 nb_pixel_total : 687181 time to create 1 rle with new method : 1.50921630859375 time for calcul the mask position with numpy : 0.05322575569152832 nb_pixel_total : 305350 time to create 1 rle with new method : 1.1027920246124268 time for calcul the mask position with numpy : 0.05113554000854492 nb_pixel_total : 25752 time to create 1 rle with old method : 0.027995586395263672 time for calcul the mask position with numpy : 0.06439375877380371 nb_pixel_total : 1726465 time to create 1 rle with new method : 1.3625595569610596 time for calcul the mask position with numpy : 0.05135345458984375 nb_pixel_total : 210 time to create 1 rle with old method : 0.1775531768798828 time for calcul the mask position with numpy : 0.056490421295166016 nb_pixel_total : 138475 time to create 1 rle with old method : 0.15020227432250977 time for calcul the mask position with numpy : 0.05270671844482422 nb_pixel_total : 84438 time to create 1 rle with old method : 0.09375119209289551 time for calcul the mask position with numpy : 0.05319476127624512 nb_pixel_total : 28861 time to create 1 rle with old method : 0.03249168395996094 time for calcul the mask position with numpy : 0.05228996276855469 nb_pixel_total : 29708 time to create 1 rle with old method : 0.033355712890625 time for calcul the mask position with numpy : 0.05208444595336914 nb_pixel_total : 43149 time to create 1 rle with old method : 0.04796195030212402 time for calcul the mask position with numpy : 0.054637908935546875 nb_pixel_total : 416134 time to create 1 rle with new method : 1.0825235843658447 time for calcul the mask position with numpy : 0.0531163215637207 nb_pixel_total : 41667 time to create 1 rle with old method : 0.04770040512084961 time for calcul the mask position with numpy : 0.056876182556152344 nb_pixel_total : 227200 time to create 1 rle with new method : 1.2357726097106934 time for calcul the mask position with numpy : 0.054958343505859375 nb_pixel_total : 49645 time to create 1 rle with old method : 0.05954408645629883 time for calcul the mask position with numpy : 0.05418586730957031 nb_pixel_total : 84162 time to create 1 rle with old method : 0.09689188003540039 time for calcul the mask position with numpy : 0.05393815040588379 nb_pixel_total : 61924 time to create 1 rle with old method : 0.07000255584716797 time for calcul the mask position with numpy : 0.053351640701293945 nb_pixel_total : 42333 time to create 1 rle with old method : 0.04774951934814453 time for calcul the mask position with numpy : 0.05670356750488281 nb_pixel_total : 411374 time to create 1 rle with new method : 1.2474517822265625 time for calcul the mask position with numpy : 0.05508995056152344 nb_pixel_total : 358817 time to create 1 rle with new method : 1.268174409866333 time for calcul the mask position with numpy : 0.05432558059692383 nb_pixel_total : 75376 time to create 1 rle with old method : 0.08524847030639648 time for calcul the mask position with numpy : 0.05503678321838379 nb_pixel_total : 356665 time to create 1 rle with new method : 1.735414981842041 time for calcul the mask position with numpy : 0.05425405502319336 nb_pixel_total : 50625 time to create 1 rle with old method : 0.058370113372802734 time for calcul the mask position with numpy : 0.0684971809387207 nb_pixel_total : 1624667 time to create 1 rle with new method : 1.1302952766418457 time for calcul the mask position with numpy : 0.0560612678527832 nb_pixel_total : 331855 time to create 1 rle with new method : 1.1567001342773438 time for calcul the mask position with numpy : 0.057213783264160156 nb_pixel_total : 53368 time to create 1 rle with old method : 0.08439278602600098 time for calcul the mask position with numpy : 0.060607194900512695 nb_pixel_total : 664073 time to create 1 rle with new method : 1.2052454948425293 time for calcul the mask position with numpy : 0.0598599910736084 nb_pixel_total : 2974 time to create 1 rle with old method : 0.005489826202392578 time for calcul the mask position with numpy : 0.06661248207092285 nb_pixel_total : 81449 time to create 1 rle with old method : 0.0947408676147461 time for calcul the mask position with numpy : 0.05810713768005371 nb_pixel_total : 470158 time to create 1 rle with new method : 1.3312828540802002 time for calcul the mask position with numpy : 0.07659125328063965 nb_pixel_total : 2525 time to create 1 rle with old method : 0.003424406051635742 time for calcul the mask position with numpy : 0.05532217025756836 nb_pixel_total : 9904 time to create 1 rle with old method : 0.012327909469604492 time for calcul the mask position with numpy : 0.06996297836303711 nb_pixel_total : 184947 time to create 1 rle with new method : 1.3861212730407715 time for calcul the mask position with numpy : 0.06315755844116211 nb_pixel_total : 41779 time to create 1 rle with old method : 0.04846978187561035 time for calcul the mask position with numpy : 0.05739712715148926 nb_pixel_total : 21278 time to create 1 rle with old method : 0.02514195442199707 time for calcul the mask position with numpy : 0.05551886558532715 nb_pixel_total : 209317 time to create 1 rle with new method : 1.4793195724487305 time for calcul the mask position with numpy : 0.056388139724731445 nb_pixel_total : 6006 time to create 1 rle with old method : 0.007258892059326172 time for calcul the mask position with numpy : 0.05977439880371094 nb_pixel_total : 110 time to create 1 rle with old method : 0.000385284423828125 time for calcul the mask position with numpy : 0.05445671081542969 nb_pixel_total : 61097 time to create 1 rle with old method : 0.08134794235229492 create new chi : 34.91050577163696 time to delete rle : 0.016765356063842773 batch 1 Loaded 57 chid ids of type : 4855 Number RLEs to save : 53116 TO DO : save crop sub photo not yet done ! save time : 10.936885118484497 nb_obj : 42 nb_hashtags : 7 time to prepare the origin masks : 45.277782917022705 time for calcul the mask position with numpy : 0.2762589454650879 nb_pixel_total : 2079400 time to create 1 rle with new method : 1.9037764072418213 time for calcul the mask position with numpy : 0.05448412895202637 nb_pixel_total : 861 time to create 1 rle with old method : 0.0015988349914550781 time for calcul the mask position with numpy : 0.056980133056640625 nb_pixel_total : 89307 time to create 1 rle with old method : 0.10480618476867676 time for calcul the mask position with numpy : 0.061920881271362305 nb_pixel_total : 178482 time to create 1 rle with new method : 1.6508684158325195 time for calcul the mask position with numpy : 0.05625796318054199 nb_pixel_total : 185448 time to create 1 rle with new method : 1.5716321468353271 time for calcul the mask position with numpy : 0.3528766632080078 nb_pixel_total : 1311952 time to create 1 rle with new method : 1.9469285011291504 time for calcul the mask position with numpy : 0.05699348449707031 nb_pixel_total : 335596 time to create 1 rle with new method : 1.8091373443603516 time for calcul the mask position with numpy : 0.05495762825012207 nb_pixel_total : 67052 time to create 1 rle with old method : 0.07440733909606934 time for calcul the mask position with numpy : 0.052249908447265625 nb_pixel_total : 31020 time to create 1 rle with old method : 0.034111976623535156 time for calcul the mask position with numpy : 0.05491065979003906 nb_pixel_total : 170442 time to create 1 rle with new method : 1.1929066181182861 time for calcul the mask position with numpy : 0.0573880672454834 nb_pixel_total : 433186 time to create 1 rle with new method : 1.2472994327545166 time for calcul the mask position with numpy : 0.05519700050354004 nb_pixel_total : 308653 time to create 1 rle with new method : 1.1758713722229004 time for calcul the mask position with numpy : 0.051190853118896484 nb_pixel_total : 418 time to create 1 rle with old method : 0.0008463859558105469 time for calcul the mask position with numpy : 0.062267303466796875 nb_pixel_total : 798415 time to create 1 rle with new method : 1.5931594371795654 time for calcul the mask position with numpy : 0.05559539794921875 nb_pixel_total : 133470 time to create 1 rle with old method : 0.15297150611877441 time for calcul the mask position with numpy : 0.05230832099914551 nb_pixel_total : 28000 time to create 1 rle with old method : 0.031152725219726562 time for calcul the mask position with numpy : 0.12077808380126953 nb_pixel_total : 1866789 time to create 1 rle with new method : 1.5381081104278564 time for calcul the mask position with numpy : 0.05908656120300293 nb_pixel_total : 354639 time to create 1 rle with new method : 1.8133363723754883 time for calcul the mask position with numpy : 0.06389641761779785 nb_pixel_total : 43184 time to create 1 rle with old method : 0.04925084114074707 time for calcul the mask position with numpy : 0.07085490226745605 nb_pixel_total : 1290964 time to create 1 rle with new method : 1.7469828128814697 time for calcul the mask position with numpy : 0.08517146110534668 nb_pixel_total : 169382 time to create 1 rle with new method : 2.4968419075012207 time for calcul the mask position with numpy : 0.05428791046142578 nb_pixel_total : 101362 time to create 1 rle with old method : 0.13799095153808594 time for calcul the mask position with numpy : 0.054122209548950195 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0018663406372070312 time for calcul the mask position with numpy : 0.05494236946105957 nb_pixel_total : 107864 time to create 1 rle with old method : 0.16129040718078613 time for calcul the mask position with numpy : 0.05504298210144043 nb_pixel_total : 124807 time to create 1 rle with old method : 0.1400587558746338 time for calcul the mask position with numpy : 0.051019906997680664 nb_pixel_total : 12 time to create 1 rle with old method : 6.508827209472656e-05 time for calcul the mask position with numpy : 0.06852912902832031 nb_pixel_total : 1499958 time to create 1 rle with new method : 1.1705467700958252 time for calcul the mask position with numpy : 0.051125288009643555 nb_pixel_total : 16594 time to create 1 rle with old method : 0.018499374389648438 time for calcul the mask position with numpy : 0.05101275444030762 nb_pixel_total : 169 time to create 1 rle with old method : 0.0003590583801269531 time for calcul the mask position with numpy : 0.05388760566711426 nb_pixel_total : 118413 time to create 1 rle with old method : 0.14750051498413086 time for calcul the mask position with numpy : 0.05504465103149414 nb_pixel_total : 64216 time to create 1 rle with old method : 0.07407498359680176 time for calcul the mask position with numpy : 0.056345462799072266 nb_pixel_total : 7110 time to create 1 rle with old method : 0.00897216796875 time for calcul the mask position with numpy : 0.055663108825683594 nb_pixel_total : 47198 time to create 1 rle with old method : 0.05176854133605957 time for calcul the mask position with numpy : 0.06127429008483887 nb_pixel_total : 600805 time to create 1 rle with new method : 1.820371150970459 time for calcul the mask position with numpy : 0.05309605598449707 nb_pixel_total : 5116 time to create 1 rle with old method : 0.005999088287353516 time for calcul the mask position with numpy : 0.05347633361816406 nb_pixel_total : 36219 time to create 1 rle with old method : 0.040721893310546875 time for calcul the mask position with numpy : 0.05389809608459473 nb_pixel_total : 128864 time to create 1 rle with old method : 0.17004680633544922 time for calcul the mask position with numpy : 0.06279635429382324 nb_pixel_total : 1461 time to create 1 rle with old method : 0.002559661865234375 time for calcul the mask position with numpy : 0.058940887451171875 nb_pixel_total : 59617 time to create 1 rle with old method : 0.06748342514038086 time for calcul the mask position with numpy : 0.05845236778259277 nb_pixel_total : 88729 time to create 1 rle with old method : 0.10193657875061035 time for calcul the mask position with numpy : 0.06377363204956055 nb_pixel_total : 56648 time to create 1 rle with old method : 0.06785345077514648 time for calcul the mask position with numpy : 0.054404258728027344 nb_pixel_total : 32783 time to create 1 rle with old method : 0.03810381889343262 time for calcul the mask position with numpy : 0.05463385581970215 nb_pixel_total : 3097 time to create 1 rle with old method : 0.0037755966186523438 create new chi : 30.251180410385132 time to delete rle : 0.00400996208190918 batch 1 Loaded 43 chid ids of type : 4855 Number RLEs to save : 44308 TO DO : save crop sub photo not yet done ! save time : 7.9767796993255615 nb_obj : 32 nb_hashtags : 9 time to prepare the origin masks : 40.52739214897156 time for calcul the mask position with numpy : 0.17395377159118652 nb_pixel_total : 1901971 time to create 1 rle with new method : 1.5216341018676758 time for calcul the mask position with numpy : 0.053818464279174805 nb_pixel_total : 28300 time to create 1 rle with old method : 0.030608654022216797 time for calcul the mask position with numpy : 0.0526738166809082 nb_pixel_total : 234839 time to create 1 rle with new method : 1.7849094867706299 time for calcul the mask position with numpy : 0.06366705894470215 nb_pixel_total : 1173135 time to create 1 rle with new method : 1.3751108646392822 time for calcul the mask position with numpy : 0.06818962097167969 nb_pixel_total : 961546 time to create 1 rle with new method : 1.0984675884246826 time for calcul the mask position with numpy : 0.05683565139770508 nb_pixel_total : 421868 time to create 1 rle with new method : 0.9046266078948975 time for calcul the mask position with numpy : 0.05202817916870117 nb_pixel_total : 63468 time to create 1 rle with old method : 0.07085013389587402 time for calcul the mask position with numpy : 0.05254721641540527 nb_pixel_total : 63119 time to create 1 rle with old method : 0.07206320762634277 time for calcul the mask position with numpy : 0.2805056571960449 nb_pixel_total : 2428210 time to create 1 rle with new method : 1.4613111019134521 time for calcul the mask position with numpy : 0.05879640579223633 nb_pixel_total : 18805 time to create 1 rle with old method : 0.022009849548339844 time for calcul the mask position with numpy : 0.05472397804260254 nb_pixel_total : 395604 time to create 1 rle with new method : 1.525435447692871 time for calcul the mask position with numpy : 0.05285525321960449 nb_pixel_total : 326395 time to create 1 rle with new method : 1.222414255142212 time for calcul the mask position with numpy : 0.05288219451904297 nb_pixel_total : 48268 time to create 1 rle with old method : 0.05482625961303711 time for calcul the mask position with numpy : 0.4213235378265381 nb_pixel_total : 3474513 time to create 1 rle with new method : 1.2050034999847412 time for calcul the mask position with numpy : 0.053377389907836914 nb_pixel_total : 6380 time to create 1 rle with old method : 0.007475376129150391 time for calcul the mask position with numpy : 0.05218839645385742 nb_pixel_total : 49722 time to create 1 rle with old method : 0.05526113510131836 time for calcul the mask position with numpy : 0.05233025550842285 nb_pixel_total : 9143 time to create 1 rle with old method : 0.010376453399658203 time for calcul the mask position with numpy : 0.05161690711975098 nb_pixel_total : 42004 time to create 1 rle with old method : 0.047669410705566406 time for calcul the mask position with numpy : 0.06841754913330078 nb_pixel_total : 87012 time to create 1 rle with old method : 0.1091468334197998 time for calcul the mask position with numpy : 0.0516505241394043 nb_pixel_total : 13758 time to create 1 rle with old method : 0.01515054702758789 time for calcul the mask position with numpy : 0.052076101303100586 nb_pixel_total : 39360 time to create 1 rle with old method : 0.045322418212890625 time for calcul the mask position with numpy : 0.05215740203857422 nb_pixel_total : 65891 time to create 1 rle with old method : 0.07305908203125 time for calcul the mask position with numpy : 0.0522618293762207 nb_pixel_total : 17 time to create 1 rle with old method : 7.104873657226562e-05 time for calcul the mask position with numpy : 0.06494021415710449 nb_pixel_total : 1525 time to create 1 rle with old method : 0.004179716110229492 time for calcul the mask position with numpy : 0.06534147262573242 nb_pixel_total : 114812 time to create 1 rle with old method : 0.1293177604675293 time for calcul the mask position with numpy : 0.053069353103637695 nb_pixel_total : 247914 time to create 1 rle with new method : 1.1886065006256104 time for calcul the mask position with numpy : 0.05228590965270996 nb_pixel_total : 238891 time to create 1 rle with new method : 1.204268217086792 time for calcul the mask position with numpy : 0.05557823181152344 nb_pixel_total : 36930 time to create 1 rle with old method : 0.04113602638244629 time for calcul the mask position with numpy : 0.05257391929626465 nb_pixel_total : 109947 time to create 1 rle with old method : 0.1249544620513916 time for calcul the mask position with numpy : 0.05397796630859375 nb_pixel_total : 2171 time to create 1 rle with old method : 0.0026857852935791016 time for calcul the mask position with numpy : 0.052572011947631836 nb_pixel_total : 136248 time to create 1 rle with old method : 0.15117263793945312 time for calcul the mask position with numpy : 0.05325198173522949 nb_pixel_total : 237303 time to create 1 rle with new method : 1.3746025562286377 time for calcul the mask position with numpy : 0.05740857124328613 nb_pixel_total : 131 time to create 1 rle with old method : 0.0005934238433837891 create new chi : 20.24085259437561 time to delete rle : 0.0051119327545166016 batch 1 Loaded 33 chid ids of type : 4855 Number RLEs to save : 35087 TO DO : save crop sub photo not yet done ! save time : 4.943488836288452 map_output_result : {1349036556: (0.4534219198382379, 'Should be the crop_list due to order', 0.5318556515119768), 1349036552: (0.4534219198382379, 'Should be the crop_list due to order', 0.3700314751443568), 1349036517: (0.4534219198382379, 'Should be the crop_list due to order', 0.27514671741003915), 1349036515: (0.4534219198382379, 'Should be the crop_list due to order', 0.5181797457106104), 1349036509: (0.4534219198382379, 'Should be the crop_list due to order', 0.11530564830782822), 1349036504: (0.4534219198382379, 'Should be the crop_list due to order', 0.4690596141716523), 1349036502: (0.4534219198382379, 'Should be the crop_list due to order', 0.7201839404225634), 1349036500: (0.4534219198382379, 'Should be the crop_list due to order', 0.627612566026876)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 8 /1349036556.Didn't retrieve data . /1349036552.Didn't retrieve data . /1349036517.Didn't retrieve data . /1349036515.Didn't retrieve data . /1349036509.Didn't retrieve data . /1349036504.Didn't retrieve data . /1349036502.Didn't retrieve data . /1349036500.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 24 time used for this insertion : 0.016083478927612305 save_final save missing photos in datou_result : time spend for datou_step_exec : 727.876631975174 time spend to save output : 0.018018722534179688 total time spend for step 5 : 727.8946506977081 step6:crop_condition Tue Apr 1 02:19:48 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4855 Loading chi in step crop for list_pids : 8 ! batch 1 Loaded 409 chid ids of type : 4855 begin to crop the class : papier param for this class : {'min_score': 0.1} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 74 About to insert : list_path_to_insert length 74 new photo from crops ! About to upload 74 photos upload in portfolio : 3015255 init cache_photo without model_param we have 74 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743466891_2339854 we have uploaded 74 photos in the portfolio 3015255 time of upload the photos Elapsed time : 34.94256591796875 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.1} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 62 About to insert : list_path_to_insert length 62 new photo from crops ! About to upload 62 photos upload in portfolio : 3015255 init cache_photo without model_param we have 62 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743466986_2339854 we have uploaded 62 photos in the portfolio 3015255 time of upload the photos Elapsed time : 26.6735897064209 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.1} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 12 About to insert : list_path_to_insert length 12 new photo from crops ! About to upload 12 photos upload in portfolio : 3015255 init cache_photo without model_param we have 12 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467020_2339854 we have uploaded 12 photos in the portfolio 3015255 time of upload the photos Elapsed time : 3.7057135105133057 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.1} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3015255 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467028_2339854 we have uploaded 3 photos in the portfolio 3015255 time of upload the photos Elapsed time : 2.5991568565368652 we have finished the crop for the class : pet_clair begin to crop the class : pehd param for this class : {'min_score': 0.1} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3015255 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467035_2339854 we have uploaded 3 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.3905305862426758 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.1} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3015255 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467043_2339854 we have uploaded 2 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.4017260074615479 we have finished the crop for the class : pet_fonce begin to crop the class : sac param for this class : {'min_score': 0.1} filtre for class : sac hashtag_id of this class : 492618350 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 3015255 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467062_2339854 we have uploaded 14 photos in the portfolio 3015255 time of upload the photos Elapsed time : 8.024075746536255 we have finished the crop for the class : sac begin to crop the class : textiles param for this class : {'min_score': 0.1} filtre for class : textiles hashtag_id of this class : 494789423 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! About to upload 6 photos upload in portfolio : 3015255 init cache_photo without model_param we have 6 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467076_2339854 we have uploaded 6 photos in the portfolio 3015255 time of upload the photos Elapsed time : 4.992350816726685 we have finished the crop for the class : textiles begin to crop the class : verre param for this class : {'min_score': 0.1} filtre for class : verre hashtag_id of this class : 492631919 begin to crop the class : organique param for this class : {'min_score': 0.1} filtre for class : organique hashtag_id of this class : 530726390 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3015255 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467085_2339854 we have uploaded 1 photos in the portfolio 3015255 time of upload the photos Elapsed time : 0.7000715732574463 we have finished the crop for the class : organique begin to crop the class : dasri param for this class : {'min_score': 0.1} filtre for class : dasri hashtag_id of this class : 1608424396 begin to crop the class : masque param for this class : {'min_score': 0.1} filtre for class : masque hashtag_id of this class : 492626781 begin to crop the class : encombrant param for this class : {'min_score': 0.1} filtre for class : encombrant hashtag_id of this class : 605975549 begin to crop the class : autre param for this class : {'min_score': 0.1} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 48 About to insert : list_path_to_insert length 48 new photo from crops ! About to upload 48 photos upload in portfolio : 3015255 init cache_photo without model_param we have 48 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467184_2339854 we have uploaded 48 photos in the portfolio 3015255 time of upload the photos Elapsed time : 21.90098214149475 we have finished the crop for the class : autre begin to crop the class : autre_emballage param for this class : {'min_score': 0.1} filtre for class : autre_emballage hashtag_id of this class : 2107760328 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3015255 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467212_2339854 we have uploaded 1 photos in the portfolio 3015255 time of upload the photos Elapsed time : 0.5514383316040039 we have finished the crop for the class : autre_emballage begin to crop the class : autre_non_emballage param for this class : {'min_score': 0.1} filtre for class : autre_non_emballage hashtag_id of this class : 2107760329 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 10 About to insert : list_path_to_insert length 10 new photo from crops ! About to upload 10 photos upload in portfolio : 3015255 init cache_photo without model_param we have 10 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467223_2339854 we have uploaded 10 photos in the portfolio 3015255 time of upload the photos Elapsed time : 3.5531580448150635 we have finished the crop for the class : autre_non_emballage begin to crop the class : environnement param for this class : {'min_score': 0.1} filtre for class : environnement hashtag_id of this class : 493012381 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 50 About to insert : list_path_to_insert length 50 new photo from crops ! About to upload 50 photos upload in portfolio : 3015255 init cache_photo without model_param we have 50 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743467319_2339854 we have uploaded 50 photos in the portfolio 3015255 time of upload the photos Elapsed time : 20.932848691940308 we have finished the crop for the class : environnement delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 286 /1349175804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349175912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349176815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349177753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 866 time used for this insertion : 0.09515881538391113 save_final save missing photos in datou_result : time spend for datou_step_exec : 571.13321185112 time spend to save output : 0.27410054206848145 total time spend for step 6 : 571.4073123931885 step7:ventilate_hashtags_in_portfolio Tue Apr 1 02:29:19 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 21920562 get user id for portfolio 21920562 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920562 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920562 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920562 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920562 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do lien utilise dans velours : https://www.fotonower.com/velours/21931265,21931266,21931267,21931268,21931269,21931274,21931276,21931277,21931278,21931279,21931280,21931281,21931283,21931284,21931285,21931286,21931287,21931288,21931289,21931290?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=21920562 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 1 /21920562. before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.01512765884399414 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.7557880878448486 time spend to save output : 0.01538705825805664 total time spend for step 7 : 3.7711751461029053 step8:final Tue Apr 1 02:29:23 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1349036556: ('0.4456697773051765',), 1349036552: ('0.4456697773051765',), 1349036517: ('0.4456697773051765',), 1349036515: ('0.4456697773051765',), 1349036509: ('0.4456697773051765',), 1349036504: ('0.4456697773051765',), 1349036502: ('0.4456697773051765',), 1349036500: ('0.4456697773051765',)} new output for save of step final : {1349036556: ('0.4456697773051765',), 1349036552: ('0.4456697773051765',), 1349036517: ('0.4456697773051765',), 1349036515: ('0.4456697773051765',), 1349036509: ('0.4456697773051765',), 1349036504: ('0.4456697773051765',), 1349036502: ('0.4456697773051765',), 1349036500: ('0.4456697773051765',)} [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 8 /1349036556.Didn't retrieve data . /1349036552.Didn't retrieve data . /1349036517.Didn't retrieve data . /1349036515.Didn't retrieve data . /1349036509.Didn't retrieve data . /1349036504.Didn't retrieve data . /1349036502.Didn't retrieve data . /1349036500.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 24 time used for this insertion : 0.014163732528686523 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12784504890441895 time spend to save output : 0.014789104461669922 total time spend for step 8 : 0.14263415336608887 step9:velours_tree Tue Apr 1 02:29:23 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 0.6814424991607666 time spend to save output : 3.600120544433594e-05 total time spend for step 9 : 0.6814785003662109 step10:send_mail_cod Tue Apr 1 02:29:24 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 complete output_args for input 2 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 3 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Auto_P21920562_01-04-2025_02_29_24.pdf 21931239 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312391743467364 21931240 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312401743467366 21931241 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312411743467368 21931242 change filename to text .change filename to text .change filename to text .imagette219312421743467369 21931243 change filename to text .change filename to text .change filename to text .imagette219312431743467369 21931244 change filename to text .change filename to text .imagette219312441743467370 21931245 imagette219312451743467370 21931246 imagette219312461743467370 21931247 imagette219312471743467370 21931248 imagette219312481743467370 21931249 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312491743467370 21931250 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312501743467371 21931251 imagette219312511743467372 21931252 change filename to text .imagette219312521743467372 21931253 imagette219312531743467372 21931254 imagette219312541743467372 21931255 imagette219312551743467372 21931256 change filename to text .imagette219312561743467372 21931257 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312571743467372 21931259 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219312591743467373 21931260 imagette219312601743467376 21931261 imagette219312611743467376 21931262 imagette219312621743467376 21931263 imagette219312631743467376 21931264 imagette219312641743467376 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21920562 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21931265,21931266,21931267,21931268,21931269,21931274,21931276,21931277,21931278,21931279,21931280,21931281,21931283,21931284,21931285,21931286,21931287,21931288,21931289,21931290?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=21920562 your option no_mail is active, we will not send the real mail to your client args[1349036556] : ((1349036556, 142.96850810668928, 492688767), (1349036556, -0.1335991071364285, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036552] : ((1349036552, 1834.5902026211782, 2107751945), (1349036552, -0.08615109103428817, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036517] : ((1349036517, 1576.010065770194, 2107751945), (1349036517, -0.13847772323998125, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036515] : ((1349036515, 2209.5831355892365, 492609224), (1349036515, -0.13436120769356075, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036509] : ((1349036509, 628.4168729001226, 492688767), (1349036509, -0.09135474149397196, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036504] : ((1349036504, 1764.3295436377416, 2107751945), (1349036504, -0.2880548233629943, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036502] : ((1349036502, 118.29706638530128, 492688767), (1349036502, -0.0980637017192748, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1349036500] : ((1349036500, 1376.6447892664648, 2107751945), (1349036500, -0.44962622359779314, 496442774), '0.4456697773051765') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.4456697773051765 2022-04-13 10:29:59 0 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21920562_01-04-2025_02_29_24.pdf results_Auto_P21920562_01-04-2025_02_29_24.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21920562_01-04-2025_02_29_24.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4741','21920562','results_Auto_P21920562_01-04-2025_02_29_24.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21920562_01-04-2025_02_29_24.pdf','pdf','','3.79','0.4456697773051765') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 8 time used for this insertion : 0.012224197387695312 save_final save missing photos in datou_result : time spend for datou_step_exec : 18.813788652420044 time spend to save output : 0.12983083724975586 total time spend for step 10 : 18.9436194896698 step11:split_time_score Tue Apr 1 02:29:43 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 1 VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('52', 1), ('53', 1), ('54', 6)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 18022025 21920562 Nombre de photos uploadées : 8 / 23040 (0%) 18022025 21920562 Nombre de photos taguées (types de déchets): 0 / 8 (0%) 18022025 21920562 Nombre de photos taguées (volume) : 0 / 8 (0%) elapsed_time : load_data_split_time_score 3.5762786865234375e-06 elapsed_time : order_list_meta_photo_and_scores 1.0251998901367188e-05 ???????? elapsed_time : fill_and_build_computed_from_old_data 0.0007431507110595703 elapsed_time : insert_dashboard_record_day_entry 0.025392770767211914 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920559 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920560 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920561 order by id desc limit 1 Qualite : 0.4456697773051765 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21920562_01-04-2025_02_29_24.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920562 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920562 AND mptpi.`type`=4855 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920563 order by id desc limit 1 Qualite : 0.38669886588856495 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21920564_31-03-2025_20_22_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21920564 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21920564 AND mptpi.`type`=4855 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'18022025': {'nb_upload': 8, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1349036556, 1349036552, 1349036517, 1349036515, 1349036509, 1349036504, 1349036502, 1349036500] Looping around the photos to save general results len do output : 1 /21920562Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036556', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036552', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036517', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036515', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036509', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036504', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036502', None, None, None, None, None, '2710271') ('4741', None, None, None, None, None, None, None, '2710271') ('4741', '21920562', '1349036500', None, None, None, None, None, '2710271') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.014225482940673828 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.6538896560668945 time spend to save output : 0.014403343200683594 total time spend for step 11 : 3.668292999267578 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 8 set_done_treatment 937.18user 550.66system 28:21.43elapsed 87%CPU (0avgtext+0avgdata 6874692maxresident)k 6591528inputs+923328outputs (157555major+70901811minor)pagefaults 0swaps