python /home/admin/mtr/script_for_cron.py -j default -m 20 -a 'python3 ~/workarea/git/Velours/python/prod/datou.py -j batch_current -C 3804540' -s carac_4877 -M 0 -S 0 -U 100,80,95 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/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', '/home/admin/workarea/git/apy', '/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 : 2068314 load datou : 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) 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 : step 0 init_dummy_multi_datou is not linked in the step_by_step architecture ! WARNING : step 1294 init_dummy_multi_datou is not linked in the step_by_step architecture ! 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 ! 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 : (photo_id, hashtag_id, score_max) was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? load thcls load pdts 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 : 4877, datou_cur_ids : ['3804540'] with mtr_portfolio_ids : ['27393009'] and first list_photo_ids : [] new path : /proc/2068314/ 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 ! 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 13611 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13613 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 13613 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 13614 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13614 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 13615 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13615 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 13621 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13621 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 13617 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13617 ventilate_hashtags_in_portfolio have less outputs used (0) than in the step definition (1) : 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 13611 doesn't seem to be define in the database( WARNING : type of input 2 of step 13613 doesn't seem to be define in the database( WARNING : output 1 of step 13611 have datatype=2 whereas input 1 of step 13614 have datatype=7 WARNING : type of output 2 of step 13614 doesn't seem to be define in the database( WARNING : type of input 1 of step 13615 doesn't seem to be define in the database( WARNING : type of output 3 of step 13614 doesn't seem to be define in the database( WARNING : type of input 1 of step 13617 doesn't seem to be define in the database( WARNING : type of input 2 of step 13621 doesn't seem to be define in the database( WARNING : output 1 of step 13615 have datatype=7 whereas input 2 of step 13621 have datatype=None WARNING : type of output 3 of step 13621 doesn't seem to be define in the database( WARNING : type of input 2 of step 13617 doesn't seem to be define in the database( WARNING : output 0 of step 13614 have datatype=1 whereas input 0 of step 13615 have datatype=2 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, thcl, merge_mask_thcl_custom, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, tfhub_classification2, argmax over limit max, limiting to limit_max 20 list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 7 ; length of list_pids : 7 ; length of list_args : 7 time to download the photos : 0.9488821029663086 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 : 9 step1:mask_detect Wed Oct 1 09:03:09 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 : 10359 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-10-01 09:03:13.695870: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-10-01 09:03:13.732588: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-10-01 09:03:13.734344: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd6c4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-01 09:03:13.734406: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-01 09:03:13.738366: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-01 09:03:13.900411: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x29b0fbc0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-01 09:03:13.900468: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-01 09:03:13.902007: 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 2025-10-01 09:03:13.902347: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 09:03:13.904403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 09:03:13.921929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 09:03:13.922298: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 09:03:13.929501: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 09:03:13.931965: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 09:03:13.950868: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 09:03:13.952323: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 09:03:13.952754: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 09:03:13.953507: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-01 09:03:13.953523: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-01 09:03:13.953532: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-01 09:03:13.955557: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9595 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. 2025-10-01 09:03:14.461399: 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 2025-10-01 09:03:14.461479: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 09:03:14.461497: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 09:03:14.461513: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 09:03:14.461539: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 09:03:14.461554: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 09:03:14.461569: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 09:03:14.461585: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 09:03:14.462862: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 09:03:14.464080: 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 2025-10-01 09:03:14.464119: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 09:03:14.464138: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 09:03:14.464154: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 09:03:14.464171: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 09:03:14.464187: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 09:03:14.464203: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 09:03:14.464220: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 09:03:14.465510: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 09:03:14.465541: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-01 09:03:14.465550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-01 09:03:14.465557: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-01 09:03:14.466876: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9595 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 : thcl2896 thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5309, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 16384, 25088, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 5, 10, 19, 20, 46), datetime.datetime(2021, 5, 10, 19, 20, 46)) {'thcl': {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'], 'list_hashtags_csv': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'svm_hashtag_type_desc': 5309, 'photo_desc_type': 5309, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', '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_convoyeur_qualipapia_nantes_poly_100521_1 NUM_CLASSES 10 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_convoyeur_qualipapia_nantes_poly_100521_1 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-10-01 09:03:23.861249: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 09:03:24.022218: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1 /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1/mask_model.h5 size_local : 256031040 size in s3 : 256031040 create time local : 2021-08-09 05:45:48 create time in s3 : 2021-08-06 18:59:51 mask_model.h5 already exist and didn't need to update list_images length : 7 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.49293 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 21 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 5 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 5 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.49293 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 21 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (1080, 1632, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 5 Detection mask done ! Trying to reset tf kernel 2068439 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5291 tf kernel not reseted sub process len(results) : 7 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 7 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 : 10583 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2896 Catched exception ! Connect or reconnect ! thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'] time for calcul the mask position with numpy : 0.001313924789428711 nb_pixel_total : 38683 time to create 1 rle with old method : 0.04472780227661133 length of segment : 229 time for calcul the mask position with numpy : 0.0004315376281738281 nb_pixel_total : 11035 time to create 1 rle with old method : 0.012918233871459961 length of segment : 133 time for calcul the mask position with numpy : 0.00036215782165527344 nb_pixel_total : 5346 time to create 1 rle with old method : 0.006143331527709961 length of segment : 150 time for calcul the mask position with numpy : 0.00021576881408691406 nb_pixel_total : 4131 time to create 1 rle with old method : 0.005315065383911133 length of segment : 59 time for calcul the mask position with numpy : 0.010802030563354492 nb_pixel_total : 266069 time to create 1 rle with new method : 0.040688276290893555 length of segment : 1427 time for calcul the mask position with numpy : 0.0022737979888916016 nb_pixel_total : 97375 time to create 1 rle with old method : 0.10695433616638184 length of segment : 370 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.001271963119506836 length of segment : 69 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 25 time for calcul the mask position with numpy : 0.000415802001953125 nb_pixel_total : 18688 time to create 1 rle with old method : 0.02106189727783203 length of segment : 199 time for calcul the mask position with numpy : 0.00035572052001953125 nb_pixel_total : 21330 time to create 1 rle with old method : 0.023775339126586914 length of segment : 174 time for calcul the mask position with numpy : 0.000125885009765625 nb_pixel_total : 5490 time to create 1 rle with old method : 0.006772518157958984 length of segment : 80 time for calcul the mask position with numpy : 0.0001690387725830078 nb_pixel_total : 4860 time to create 1 rle with old method : 0.006621599197387695 length of segment : 64 time for calcul the mask position with numpy : 0.0007870197296142578 nb_pixel_total : 16939 time to create 1 rle with old method : 0.028481483459472656 length of segment : 134 time for calcul the mask position with numpy : 0.0005102157592773438 nb_pixel_total : 18846 time to create 1 rle with old method : 0.027790069580078125 length of segment : 139 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 3266 time to create 1 rle with old method : 0.003974199295043945 length of segment : 75 time for calcul the mask position with numpy : 0.00042819976806640625 nb_pixel_total : 9468 time to create 1 rle with old method : 0.011465072631835938 length of segment : 306 time for calcul the mask position with numpy : 0.0004954338073730469 nb_pixel_total : 1688 time to create 1 rle with old method : 0.0027866363525390625 length of segment : 180 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 3672 time to create 1 rle with old method : 0.00443577766418457 length of segment : 64 time for calcul the mask position with numpy : 0.00035309791564941406 nb_pixel_total : 18162 time to create 1 rle with old method : 0.021259307861328125 length of segment : 153 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005788803100585938 length of segment : 30 time for calcul the mask position with numpy : 0.0012297630310058594 nb_pixel_total : 90087 time to create 1 rle with old method : 0.10288619995117188 length of segment : 457 time for calcul the mask position with numpy : 0.00026226043701171875 nb_pixel_total : 16974 time to create 1 rle with old method : 0.019654035568237305 length of segment : 128 time for calcul the mask position with numpy : 0.007596492767333984 nb_pixel_total : 477535 time to create 1 rle with new method : 0.05250430107116699 length of segment : 1253 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 2439 time to create 1 rle with old method : 0.0031080245971679688 length of segment : 73 time for calcul the mask position with numpy : 0.002454996109008789 nb_pixel_total : 124604 time to create 1 rle with old method : 0.1401841640472412 length of segment : 800 time for calcul the mask position with numpy : 0.0020263195037841797 nb_pixel_total : 103236 time to create 1 rle with old method : 0.1179358959197998 length of segment : 434 time for calcul the mask position with numpy : 0.0001392364501953125 nb_pixel_total : 4019 time to create 1 rle with old method : 0.00503230094909668 length of segment : 95 time for calcul the mask position with numpy : 0.0002448558807373047 nb_pixel_total : 6328 time to create 1 rle with old method : 0.007922172546386719 length of segment : 89 time for calcul the mask position with numpy : 0.00033354759216308594 nb_pixel_total : 5377 time to create 1 rle with old method : 0.006804704666137695 length of segment : 128 time for calcul the mask position with numpy : 0.00012922286987304688 nb_pixel_total : 5820 time to create 1 rle with old method : 0.007009029388427734 length of segment : 82 time for calcul the mask position with numpy : 0.00048828125 nb_pixel_total : 18009 time to create 1 rle with old method : 0.021645307540893555 length of segment : 139 time for calcul the mask position with numpy : 0.0171816349029541 nb_pixel_total : 992271 time to create 1 rle with new method : 0.03458666801452637 length of segment : 1693 time for calcul the mask position with numpy : 0.0018122196197509766 nb_pixel_total : 125351 time to create 1 rle with old method : 0.14552831649780273 length of segment : 360 time for calcul the mask position with numpy : 0.0014166831970214844 nb_pixel_total : 90202 time to create 1 rle with old method : 0.10619115829467773 length of segment : 369 time for calcul the mask position with numpy : 0.016754865646362305 nb_pixel_total : 964712 time to create 1 rle with new method : 0.08361673355102539 length of segment : 2646 time for calcul the mask position with numpy : 0.0013155937194824219 nb_pixel_total : 87135 time to create 1 rle with old method : 0.10152029991149902 length of segment : 354 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 2102 time to create 1 rle with old method : 0.002639293670654297 length of segment : 62 time for calcul the mask position with numpy : 0.0021185874938964844 nb_pixel_total : 135979 time to create 1 rle with old method : 0.15854430198669434 length of segment : 540 time for calcul the mask position with numpy : 0.0022954940795898438 nb_pixel_total : 138134 time to create 1 rle with old method : 0.16113972663879395 length of segment : 912 time for calcul the mask position with numpy : 0.001186370849609375 nb_pixel_total : 38682 time to create 1 rle with old method : 0.0455317497253418 length of segment : 229 time for calcul the mask position with numpy : 0.0004191398620605469 nb_pixel_total : 11036 time to create 1 rle with old method : 0.013157844543457031 length of segment : 133 time for calcul the mask position with numpy : 0.00036263465881347656 nb_pixel_total : 5346 time to create 1 rle with old method : 0.006598949432373047 length of segment : 150 time for calcul the mask position with numpy : 0.0002105236053466797 nb_pixel_total : 4131 time to create 1 rle with old method : 0.005422353744506836 length of segment : 59 time for calcul the mask position with numpy : 0.01088857650756836 nb_pixel_total : 266014 time to create 1 rle with new method : 0.02180624008178711 length of segment : 1427 time for calcul the mask position with numpy : 0.002292633056640625 nb_pixel_total : 97375 time to create 1 rle with old method : 0.11129283905029297 length of segment : 370 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0013403892517089844 length of segment : 69 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 25 time for calcul the mask position with numpy : 0.0004353523254394531 nb_pixel_total : 18684 time to create 1 rle with old method : 0.022333621978759766 length of segment : 199 time for calcul the mask position with numpy : 0.0003600120544433594 nb_pixel_total : 21326 time to create 1 rle with old method : 0.025246858596801758 length of segment : 174 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 5490 time to create 1 rle with old method : 0.0065653324127197266 length of segment : 80 time for calcul the mask position with numpy : 0.00017642974853515625 nb_pixel_total : 4860 time to create 1 rle with old method : 0.006268024444580078 length of segment : 64 time for calcul the mask position with numpy : 0.0006237030029296875 nb_pixel_total : 16941 time to create 1 rle with old method : 0.02030181884765625 length of segment : 134 time for calcul the mask position with numpy : 0.0004031658172607422 nb_pixel_total : 18846 time to create 1 rle with old method : 0.022917747497558594 length of segment : 139 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 3266 time to create 1 rle with old method : 0.003959178924560547 length of segment : 75 time for calcul the mask position with numpy : 0.0004417896270751953 nb_pixel_total : 9511 time to create 1 rle with old method : 0.011510133743286133 length of segment : 306 time for calcul the mask position with numpy : 0.00047588348388671875 nb_pixel_total : 1707 time to create 1 rle with old method : 0.002797365188598633 length of segment : 182 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 3671 time to create 1 rle with old method : 0.0046138763427734375 length of segment : 64 time for calcul the mask position with numpy : 0.0003745555877685547 nb_pixel_total : 18163 time to create 1 rle with old method : 0.022014379501342773 length of segment : 153 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006492137908935547 length of segment : 30 time for calcul the mask position with numpy : 0.0024635791778564453 nb_pixel_total : 90089 time to create 1 rle with old method : 0.10455799102783203 length of segment : 457 time for calcul the mask position with numpy : 0.0004742145538330078 nb_pixel_total : 16974 time to create 1 rle with old method : 0.02010059356689453 length of segment : 128 time for calcul the mask position with numpy : 0.013218164443969727 nb_pixel_total : 477436 time to create 1 rle with new method : 0.05170178413391113 length of segment : 1254 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 2439 time to create 1 rle with old method : 0.003136157989501953 length of segment : 73 time for calcul the mask position with numpy : 0.002282381057739258 nb_pixel_total : 124580 time to create 1 rle with old method : 0.14156031608581543 length of segment : 800 time for calcul the mask position with numpy : 0.0014941692352294922 nb_pixel_total : 103230 time to create 1 rle with old method : 0.1170949935913086 length of segment : 435 time for calcul the mask position with numpy : 0.00011873245239257812 nb_pixel_total : 4020 time to create 1 rle with old method : 0.0048999786376953125 length of segment : 95 time for calcul the mask position with numpy : 0.00018405914306640625 nb_pixel_total : 6328 time to create 1 rle with old method : 0.007585287094116211 length of segment : 89 time for calcul the mask position with numpy : 0.00015544891357421875 nb_pixel_total : 5368 time to create 1 rle with old method : 0.006777763366699219 length of segment : 128 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 5820 time to create 1 rle with old method : 0.006846904754638672 length of segment : 82 time for calcul the mask position with numpy : 0.00030231475830078125 nb_pixel_total : 18009 time to create 1 rle with old method : 0.021067142486572266 length of segment : 139 time for calcul the mask position with numpy : 0.013684272766113281 nb_pixel_total : 992275 time to create 1 rle with new method : 0.0372004508972168 length of segment : 1692 time for calcul the mask position with numpy : 0.0018765926361083984 nb_pixel_total : 125356 time to create 1 rle with old method : 0.14995384216308594 length of segment : 360 time for calcul the mask position with numpy : 0.0013222694396972656 nb_pixel_total : 90201 time to create 1 rle with old method : 0.10292696952819824 length of segment : 369 time spent for convertir_results : 7.394773244857788 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 73 chid ids of type : 3663 Number RLEs to save : 24837 save missing photos in datou_result : time spend for datou_step_exec : 33.43073034286499 time spend to save output : 2.6406924724578857 total time spend for step 1 : 36.071422815322876 step2:crop_condition Wed Oct 1 09:03:45 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 Loading chi in step crop with photo_hashtag_type : 3663 Loading chi in step crop for list_pids : 7 ! batch 1 Loaded 73 chid ids of type : 3663 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : teint_dans_la_masse param for this class : {'min_score': 0.7} filtre for class : teint_dans_la_masse hashtag_id of this class : 2107752385 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles 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 ! we have finished the crop for the class : teint_dans_la_masse begin to crop the class : autre_refus param for this class : {'min_score': 0.5} filtre for class : autre_refus hashtag_id of this class : 2107752406 we have both polygon and rles 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 ! we have finished the crop for the class : autre_refus begin to crop the class : carton_gris param for this class : {'min_score': 0.5} filtre for class : carton_gris hashtag_id of this class : 2107753020 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! we have finished the crop for the class : carton_gris begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 21 About to insert : list_path_to_insert length 21 new photo from crops ! we have finished the crop for the class : cartonnette begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! we have finished the crop for the class : carton_brun begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 begin to crop the class : kraft param for this class : {'min_score': 0.5} filtre for class : kraft hashtag_id of this class : 493202403 begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1387088074, 1387088059, 1387088055, 1387088051, 1387087975, 1387087973, 1387087967] Looping around the photos to save general results len do output : 42 /-3981896250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981896318Didn'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 ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088074', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088059', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088055', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088051', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087975', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087973', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087967', None, None, None, None, None, '3804540') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 133 time used for this insertion : 0.042972564697265625 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.919073820114136 time spend to save output : 0.04448246955871582 total time spend for step 2 : 5.963556289672852 step3:thcl Wed Oct 1 09:03:51 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 Beginning of datou step Thcl ! nombre de thcls : 2 we are using the classfication for multi_thcl [2456, 2868] time to import caffe and check if the image exist : 0.007589578628540039 time to convert the images to numpy array : 5.0067901611328125e-06 time to import caffe and check if the image exist : 0.01279902458190918 time to convert the images to numpy array : 0.01074981689453125 time to import caffe and check if the image exist : 0.012594461441040039 time to convert the images to numpy array : 0.02448868751525879 time to import caffe and check if the image exist : 0.010999441146850586 time to convert the images to numpy array : 0.02715015411376953 time to import caffe and check if the image exist : 0.010375022888183594 time to convert the images to numpy array : 0.029940366744995117 time to import caffe and check if the image exist : 0.01108098030090332 time to convert the images to numpy array : 0.031423330307006836 time to import caffe and check if the image exist : 0.011030912399291992 time to convert the images to numpy array : 0.031235694885253906 time to import caffe and check if the image exist : 0.01212310791015625 time to convert the images to numpy array : 0.03587174415588379 time to import caffe and check if the image exist : 0.016319751739501953 time to convert the images to numpy array : 0.03384971618652344 time to import caffe and check if the image exist : 0.015526294708251953 time to convert the images to numpy array : 0.038411617279052734 total time to convert the images to numpy array : 0.2920572757720947 list photo_ids error: [] list photo_ids correct : [-3981896303, -3981896318, -3981896292, -3981896310, -3981896286, -3981896266, -3981896277, -3981896265, -3981896263, -3981896261, -3981896278, -3981896280, -3981896250, -3981896262, -3981896251, -3981896260, -3981896253, -3981896271, -3981896289, -3981896301, -3981896290, -3981896299, -3981896294, -3981896304, -3981896302, -3981896300, -3981896317, -3981896305, -3981896316, -3981896258, -3981896259, -3981896255, -3981896319, -3981896314, -3981896322, -3981896264, -3981896279, -3981896275, -3981896283, -3981896285, -3981896297, -3981896298] number of photos to traite : 42 try to delete the photos incorrect in DB tagging for thcl : 2456 To do loadFromThcl(), then load ParamDescType : thcl2456 thcls : [{'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'}] thcl {'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'} Update svm_hashtag_type_desc : 4999 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) To loadFromThcl() : net_4999 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10583 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_qualipapia_papier_refus_from_vlg_data_aug Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_qualipapia_papier_refus_from_vlg_data_aug model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel size_local : 44972172 size in s3 : 44972172 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 caffemodel already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt size_local : 17311 size in s3 : 17311 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:51 mean.npy already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/synset_words.txt size_local : 57 size in s3 : 57 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/:/home/admin/workarea/git/apy/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt caffemodel_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10361 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.2601759433746338 time used to do the prediction : 0.14490914344787598 we don't save the descriptors for this thcl 2456 tagging for thcl : 2868 To do loadFromThcl(), then load ParamDescType : thcl2868 thcls : [{'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'}] thcl {'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'} Update svm_hashtag_type_desc : 5288 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) To loadFromThcl() : net_5288 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10359 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_papier_nantes_300421 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_papier_nantes_300421 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_papier_nantes_300421 /data/models_weight/learn_papier_nantes_300421/caffemodel size_local : 44791983 size in s3 : 44791983 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:13 caffemodel already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/deploy.prototxt size_local : 17255 size in s3 : 17255 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:12 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:14 mean.npy already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/synset_words.txt size_local : 331 size in s3 : 331 create time local : 2021-08-09 05:56:00 create time in s3 : 2021-08-06 19:22:12 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/:/home/admin/workarea/git/apy/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_papier_nantes_300421/deploy.prototxt caffemodel_filename : /data/models_weight/learn_papier_nantes_300421/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10359 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.2790682315826416 time used to do the prediction : 0.10857892036437988 we don't save the descriptors for this thcl 2868 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos test new format of the output of the step_thcl begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 0 time used for this insertion : 1.5735626220703125e-05 save missing photos in datou_result : time spend for datou_step_exec : 7.998491287231445 time spend to save output : 0.0003750324249267578 total time spend for step 3 : 7.998866319656372 step4:merge_mask_thcl_custom Wed Oct 1 09:03:59 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 ! complete output_args for input 1 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 2 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step merge_mask_thcl_custom batch 1 Loaded 73 chid ids of type : 3663 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++As expected we have just one thcl present End of step merge_mask_thcl_custom Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : merge_mask_thcl_custom we use saveGeneral [1387088074, 1387088059, 1387088055, 1387088051, 1387087975, 1387087973, 1387087967] Looping around the photos to save general results len do output : 7 /1387088074Didn't retrieve data .Didn't retrieve data . /1387088059Didn't retrieve data .Didn't retrieve data . /1387088055Didn't retrieve data .Didn't retrieve data . /1387088051Didn't retrieve data .Didn't retrieve data . /1387087975Didn't retrieve data .Didn't retrieve data . /1387087973Didn't retrieve data .Didn't retrieve data . /1387087967Didn'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 : Managing all output in save final without adding information in the mtr_datou_result ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088074', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088059', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088055', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088051', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087975', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087973', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087967', None, None, None, None, None, '3804540') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 21 time used for this insertion : 0.03760337829589844 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.1948106288909912 time spend to save output : 0.03804516792297363 total time spend for step 4 : 0.23285579681396484 step5:rle_unique_nms_with_priority Wed Oct 1 09:04:00 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 Begin step rle-unique-nms nb_obj : 18 nb_hashtags : 6 time to prepare the origin masks : 3.2221362590789795 time for calcul the mask position with numpy : 0.040419816970825195 nb_pixel_total : 1244136 time to create 1 rle with new method : 0.22362685203552246 time for calcul the mask position with numpy : 0.005686044692993164 nb_pixel_total : 20732 time to create 1 rle with old method : 0.023054122924804688 time for calcul the mask position with numpy : 0.005243539810180664 nb_pixel_total : 1885 time to create 1 rle with old method : 0.002387523651123047 time for calcul the mask position with numpy : 0.005158185958862305 nb_pixel_total : 5452 time to create 1 rle with old method : 0.00629878044128418 time for calcul the mask position with numpy : 0.00546717643737793 nb_pixel_total : 16911 time to create 1 rle with old method : 0.01929020881652832 time for calcul the mask position with numpy : 0.0051422119140625 nb_pixel_total : 18794 time to create 1 rle with old method : 0.021882295608520508 time for calcul the mask position with numpy : 0.005476951599121094 nb_pixel_total : 2748 time to create 1 rle with old method : 0.003186941146850586 time for calcul the mask position with numpy : 0.005349159240722656 nb_pixel_total : 11025 time to create 1 rle with old method : 0.012650728225708008 time for calcul the mask position with numpy : 0.005364418029785156 nb_pixel_total : 9 time to create 1 rle with old method : 0.00013113021850585938 time for calcul the mask position with numpy : 0.005380392074584961 nb_pixel_total : 4835 time to create 1 rle with old method : 0.005684852600097656 time for calcul the mask position with numpy : 0.005055427551269531 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003039836883544922 time for calcul the mask position with numpy : 0.005167961120605469 nb_pixel_total : 38590 time to create 1 rle with old method : 0.04379606246948242 time for calcul the mask position with numpy : 0.0051915645599365234 nb_pixel_total : 997 time to create 1 rle with old method : 0.0011138916015625 time for calcul the mask position with numpy : 0.006655216217041016 nb_pixel_total : 264722 time to create 1 rle with new method : 0.06675529479980469 time for calcul the mask position with numpy : 0.005324840545654297 nb_pixel_total : 5288 time to create 1 rle with old method : 0.0066432952880859375 time for calcul the mask position with numpy : 0.005888223648071289 nb_pixel_total : 97277 time to create 1 rle with old method : 0.10920429229736328 time for calcul the mask position with numpy : 0.005744218826293945 nb_pixel_total : 18618 time to create 1 rle with old method : 0.021520137786865234 time for calcul the mask position with numpy : 0.005206108093261719 nb_pixel_total : 8645 time to create 1 rle with old method : 0.010256767272949219 time for calcul the mask position with numpy : 0.005512714385986328 nb_pixel_total : 1656 time to create 1 rle with old method : 0.0020051002502441406 create new chi : 0.7257304191589355 time to delete rle : 0.0706636905670166 batch 1 Loaded 19 chid ids of type : 3726 Number RLEs to save : 8610 TO DO : save crop sub photo not yet done ! save time : 0.9654591083526611 nb_obj : 12 nb_hashtags : 4 time to prepare the origin masks : 1.281982421875 time for calcul the mask position with numpy : 0.016092300415039062 nb_pixel_total : 956466 time to create 1 rle with new method : 0.03625226020812988 time for calcul the mask position with numpy : 0.008559942245483398 nb_pixel_total : 177 time to create 1 rle with old method : 0.00040268898010253906 time for calcul the mask position with numpy : 0.005319356918334961 nb_pixel_total : 17903 time to create 1 rle with old method : 0.020528554916381836 time for calcul the mask position with numpy : 0.005295991897583008 nb_pixel_total : 3969 time to create 1 rle with old method : 0.004602909088134766 time for calcul the mask position with numpy : 0.008806228637695312 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007038116455078125 time for calcul the mask position with numpy : 0.005918741226196289 nb_pixel_total : 107762 time to create 1 rle with old method : 0.1218721866607666 time for calcul the mask position with numpy : 0.005986213684082031 nb_pixel_total : 2424 time to create 1 rle with old method : 0.004794120788574219 time for calcul the mask position with numpy : 0.00656580924987793 nb_pixel_total : 5801 time to create 1 rle with old method : 0.006958961486816406 time for calcul the mask position with numpy : 0.005614519119262695 nb_pixel_total : 103002 time to create 1 rle with old method : 0.11650753021240234 time for calcul the mask position with numpy : 0.00855875015258789 nb_pixel_total : 469128 time to create 1 rle with new method : 0.06977391242980957 time for calcul the mask position with numpy : 0.00514674186706543 nb_pixel_total : 5359 time to create 1 rle with old method : 0.006325244903564453 time for calcul the mask position with numpy : 0.005731821060180664 nb_pixel_total : 89603 time to create 1 rle with old method : 0.10942363739013672 time for calcul the mask position with numpy : 0.00547027587890625 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005724430084228516 create new chi : 0.6109232902526855 time to delete rle : 0.0007510185241699219 batch 1 Loaded 13 chid ids of type : 3726 Number RLEs to save : 7890 TO DO : save crop sub photo not yet done ! save time : 0.8845372200012207 nb_obj : 3 nb_hashtags : 2 time to prepare the origin masks : 0.2815563678741455 time for calcul the mask position with numpy : 0.009945392608642578 nb_pixel_total : 664743 time to create 1 rle with new method : 0.027008771896362305 time for calcul the mask position with numpy : 0.005611896514892578 nb_pixel_total : 21424 time to create 1 rle with old method : 0.024888038635253906 time for calcul the mask position with numpy : 0.012567996978759766 nb_pixel_total : 986301 time to create 1 rle with new method : 0.0260617733001709 time for calcul the mask position with numpy : 0.0054013729095458984 nb_pixel_total : 90092 time to create 1 rle with old method : 0.10138511657714844 create new chi : 0.22237014770507812 time to delete rle : 0.0004417896270751953 batch 1 Loaded 4 chid ids of type : 3726 Number RLEs to save : 5373 TO DO : save crop sub photo not yet done ! save time : 0.6576027870178223 nb_obj : 5 nb_hashtags : 3 time to prepare the origin masks : 0.39914536476135254 time for calcul the mask position with numpy : 0.013170719146728516 nb_pixel_total : 666488 time to create 1 rle with new method : 0.02989792823791504 time for calcul the mask position with numpy : 0.0052759647369384766 nb_pixel_total : 2095 time to create 1 rle with old method : 0.002436399459838867 time for calcul the mask position with numpy : 0.0056345462799072266 nb_pixel_total : 48414 time to create 1 rle with old method : 0.05886483192443848 time for calcul the mask position with numpy : 0.005263566970825195 nb_pixel_total : 11890 time to create 1 rle with old method : 0.013996601104736328 time for calcul the mask position with numpy : 0.012629985809326172 nb_pixel_total : 946603 time to create 1 rle with new method : 0.028990745544433594 time for calcul the mask position with numpy : 0.005902528762817383 nb_pixel_total : 87070 time to create 1 rle with old method : 0.1035468578338623 create new chi : 0.2866816520690918 time to delete rle : 0.0008862018585205078 batch 1 Loaded 6 chid ids of type : 3726 Number RLEs to save : 8217 TO DO : save crop sub photo not yet done ! save time : 0.9251699447631836 nb_obj : 18 nb_hashtags : 6 time to prepare the origin masks : 2.2775278091430664 time for calcul the mask position with numpy : 0.0394587516784668 nb_pixel_total : 1244940 time to create 1 rle with new method : 0.06825637817382812 time for calcul the mask position with numpy : 0.005898475646972656 nb_pixel_total : 20732 time to create 1 rle with old method : 0.025498151779174805 time for calcul the mask position with numpy : 0.005345344543457031 nb_pixel_total : 1883 time to create 1 rle with old method : 0.0023889541625976562 time for calcul the mask position with numpy : 0.0050067901611328125 nb_pixel_total : 5452 time to create 1 rle with old method : 0.006140232086181641 time for calcul the mask position with numpy : 0.005367755889892578 nb_pixel_total : 16925 time to create 1 rle with old method : 0.019079208374023438 time for calcul the mask position with numpy : 0.005262851715087891 nb_pixel_total : 18796 time to create 1 rle with old method : 0.02644801139831543 time for calcul the mask position with numpy : 0.005558967590332031 nb_pixel_total : 2749 time to create 1 rle with old method : 0.0032377243041992188 time for calcul the mask position with numpy : 0.005148172378540039 nb_pixel_total : 11022 time to create 1 rle with old method : 0.012764215469360352 time for calcul the mask position with numpy : 0.005248308181762695 nb_pixel_total : 9 time to create 1 rle with old method : 0.00012922286987304688 time for calcul the mask position with numpy : 0.00513005256652832 nb_pixel_total : 4835 time to create 1 rle with old method : 0.005639076232910156 time for calcul the mask position with numpy : 0.005007028579711914 nb_pixel_total : 240 time to create 1 rle with old method : 0.000301361083984375 time for calcul the mask position with numpy : 0.005593538284301758 nb_pixel_total : 38588 time to create 1 rle with old method : 0.04491925239562988 time for calcul the mask position with numpy : 0.005613565444946289 nb_pixel_total : 997 time to create 1 rle with old method : 0.0011131763458251953 time for calcul the mask position with numpy : 0.0076940059661865234 nb_pixel_total : 263890 time to create 1 rle with new method : 0.09092569351196289 time for calcul the mask position with numpy : 0.006478548049926758 nb_pixel_total : 5275 time to create 1 rle with old method : 0.006780147552490234 time for calcul the mask position with numpy : 0.007545948028564453 nb_pixel_total : 97281 time to create 1 rle with old method : 0.1118927001953125 time for calcul the mask position with numpy : 0.005534648895263672 nb_pixel_total : 18605 time to create 1 rle with old method : 0.021019935607910156 time for calcul the mask position with numpy : 0.0064640045166015625 nb_pixel_total : 8664 time to create 1 rle with old method : 0.009936332702636719 time for calcul the mask position with numpy : 0.005278587341308594 nb_pixel_total : 1677 time to create 1 rle with old method : 0.0021800994873046875 create new chi : 0.6093707084655762 time to delete rle : 0.0009224414825439453 batch 1 Loaded 19 chid ids of type : 3726 Number RLEs to save : 8600 TO DO : save crop sub photo not yet done ! save time : 0.9834356307983398 nb_obj : 12 nb_hashtags : 4 time to prepare the origin masks : 0.8490757942199707 time for calcul the mask position with numpy : 0.012976646423339844 nb_pixel_total : 954850 time to create 1 rle with new method : 0.030950069427490234 time for calcul the mask position with numpy : 0.005528450012207031 nb_pixel_total : 176 time to create 1 rle with old method : 0.00041031837463378906 time for calcul the mask position with numpy : 0.005341529846191406 nb_pixel_total : 17903 time to create 1 rle with old method : 0.02056288719177246 time for calcul the mask position with numpy : 0.005026578903198242 nb_pixel_total : 3978 time to create 1 rle with old method : 0.004459857940673828 time for calcul the mask position with numpy : 0.004896402359008789 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007135868072509766 time for calcul the mask position with numpy : 0.005552530288696289 nb_pixel_total : 108178 time to create 1 rle with old method : 0.12231206893920898 time for calcul the mask position with numpy : 0.005294084548950195 nb_pixel_total : 2424 time to create 1 rle with old method : 0.0028922557830810547 time for calcul the mask position with numpy : 0.0049800872802734375 nb_pixel_total : 5801 time to create 1 rle with old method : 0.006636142730712891 time for calcul the mask position with numpy : 0.005735635757446289 nb_pixel_total : 102813 time to create 1 rle with old method : 0.11741828918457031 time for calcul the mask position with numpy : 0.005303621292114258 nb_pixel_total : 5307 time to create 1 rle with old method : 0.0063440799713134766 time for calcul the mask position with numpy : 0.009577274322509766 nb_pixel_total : 470544 time to create 1 rle with new method : 0.1819591522216797 time for calcul the mask position with numpy : 0.005949735641479492 nb_pixel_total : 89620 time to create 1 rle with old method : 0.10721087455749512 time for calcul the mask position with numpy : 0.005334138870239258 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005464553833007812 create new chi : 0.7006564140319824 time to delete rle : 0.0007078647613525391 batch 1 Loaded 13 chid ids of type : 3726 Number RLEs to save : 7884 TO DO : save crop sub photo not yet done ! save time : 0.8819715976715088 nb_obj : 3 nb_hashtags : 2 time to prepare the origin masks : 0.2602100372314453 time for calcul the mask position with numpy : 0.00978994369506836 nb_pixel_total : 664770 time to create 1 rle with new method : 0.026790618896484375 time for calcul the mask position with numpy : 0.0053081512451171875 nb_pixel_total : 21370 time to create 1 rle with old method : 0.02525019645690918 time for calcul the mask position with numpy : 0.012098312377929688 nb_pixel_total : 986303 time to create 1 rle with new method : 0.23275232315063477 time for calcul the mask position with numpy : 0.005521059036254883 nb_pixel_total : 90117 time to create 1 rle with old method : 0.10334515571594238 create new chi : 0.44356822967529297 time to delete rle : 0.00047326087951660156 batch 1 Loaded 4 chid ids of type : 3726 Number RLEs to save : 5364 TO DO : save crop sub photo not yet done ! save time : 0.6596817970275879 map_output_result : {1387088074: (0.0, 'Should be the crop_list due to order', 0.0), 1387088059: (0.0, 'Should be the crop_list due to order', 0.0), 1387088055: (0.0, 'Should be the crop_list due to order', 0.0), 1387088051: (0.0, 'Should be the crop_list due to order', 0.0), 1387087975: (0.0, 'Should be the crop_list due to order', 0.0), 1387087973: (0.0, 'Should be the crop_list due to order', 0.0), 1387087967: (0.0, 'Should be the crop_list due to order', 0.0)} 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 [1387088074, 1387088059, 1387088055, 1387088051, 1387087975, 1387087973, 1387087967] Looping around the photos to save general results len do output : 7 /1387088074.Didn't retrieve data . /1387088059.Didn't retrieve data . /1387088055.Didn't retrieve data . /1387088051.Didn't retrieve data . /1387087975.Didn't retrieve data . /1387087973.Didn't retrieve data . /1387087967.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 ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088074', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088059', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088055', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088051', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087975', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087973', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087967', None, None, None, None, None, '3804540') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 21 time used for this insertion : 0.036064863204956055 save_final save missing photos in datou_result : time spend for datou_step_exec : 18.436990976333618 time spend to save output : 0.03650784492492676 total time spend for step 5 : 18.473498821258545 step6:crop_condition Wed Oct 1 09:04:18 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 : 3726 Loading chi in step crop for list_pids : 7 ! batch 1 Loaded 78 chid ids of type : 3726 begin to crop the class : teint_dans_la_masse param for this class : {'min_score': 0.7} filtre for class : teint_dans_la_masse hashtag_id of this class : 2107752385 Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 4869462 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1759302260_2068314 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302260), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088074_8bccd31a7dd0d04d85d2c6df1038ca6d_rle_crop_3981896548_0.png', 0, 289, 226, 0, 1759302260,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302260), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088074_8bccd31a7dd0d04d85d2c6df1038ca6d_rle_crop_3981896546_0.png', 0, 144, 64, 0, 1759302260,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302260), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087975_e7df39e119f5c00835b1e4991e18a7b8_rle_crop_3981896644_0.png', 0, 289, 226, 0, 1759302260,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302260), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087975_e7df39e119f5c00835b1e4991e18a7b8_rle_crop_3981896642_0.png', 0, 144, 64, 0, 1759302260,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 4 photos in the portfolio 4869462 time of upload the photos Elapsed time : 1.6048369407653809 we have finished the crop for the class : teint_dans_la_masse begin to crop the class : autre_refus param for this class : {'min_score': 0.5} filtre for class : autre_refus hashtag_id of this class : 2107752406 Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 4869462 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1759302262_2068314 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302262), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088074_8bccd31a7dd0d04d85d2c6df1038ca6d_rle_crop_3981896543_0.png', 0, 69, 74, 0, 1759302262,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302262), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088074_8bccd31a7dd0d04d85d2c6df1038ca6d_rle_crop_3981896542_0.png', 0, 172, 138, 0, 1759302262,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302262), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087975_e7df39e119f5c00835b1e4991e18a7b8_rle_crop_3981896639_0.png', 0, 69, 74, 0, 1759302262,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302262), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087975_e7df39e119f5c00835b1e4991e18a7b8_rle_crop_3981896638_0.png', 0, 172, 138, 0, 1759302262,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 4 photos in the portfolio 4869462 time of upload the photos Elapsed time : 1.5884649753570557 we have finished the crop for the class : autre_refus begin to crop the class : carton_gris param for this class : {'min_score': 0.5} filtre for class : carton_gris hashtag_id of this class : 2107753020 begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 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 : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1759302264_2068314 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302264), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088059_784908a55846f3b9d9f6bc76d0e3f172_rle_crop_3981896563_0.png', 0, 91, 82, 0, 1759302264,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302264), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087973_ab0cdbff417fc978fb2fab20f35241e9_rle_crop_3981896813_0.png', 0, 91, 82, 0, 1759302264,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9339940547943115 we have finished the crop for the class : carton_brun begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 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 : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1759302265_2068314 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302265), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387088074_8bccd31a7dd0d04d85d2c6df1038ca6d_rle_crop_3981896540_0.png', 0, 129, 75, 0, 1759302265,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1759302265), 0.0, 0.0, 14, '', 0, 0, '1759302189_2068314_1387087975_e7df39e119f5c00835b1e4991e18a7b8_rle_crop_3981896636_0.png', 0, 129, 75, 0, 1759302265,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9553256034851074 we have finished the crop for the class : plastique begin to crop the class : kraft param for this class : {'min_score': 0.5} filtre for class : kraft hashtag_id of this class : 493202403 begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1387088074, 1387088059, 1387088055, 1387088051, 1387087975, 1387087973, 1387087967] Looping around the photos to save general results len do output : 12 /1387092697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1387092709Didn'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 ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088074', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088059', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088055', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387088051', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087975', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087973', None, None, None, None, None, '3804540') ('4877', None, None, None, None, None, None, None, '3804540') ('4877', '27393009', '1387087967', None, None, None, None, None, '3804540') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 43 time used for this insertion : 0.04824686050415039 Command terminated by signal 15 37.63user 28.63system 1:20.96elapsed 81%CPU (0avgtext+0avgdata 2760932maxresident)k 1667408inputs+11872outputs (4962major+1831922minor)pagefaults 0swaps