python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' -a 4746 -l 30 ' -s datou_current_4746 -M 0 -S 0 -U 95,95,120 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 3036102 load datou : 4746 # 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 ! 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 14102 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13182 split_time_score_with_photo have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13182 split_time_score_with_photo is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 14090 launch_next_datou_same_portfolio is not consistent : 1 used against 0 in the step definition ! 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 1 of step 13182 doesn't seem to be define in the database( WARNING : type of input 0 of step 14090 doesn't seem to be define in the database( WARNING : type of output 2 of step 14102 doesn't seem to be define in the database( WARNING : type of input 2 of step 13182 doesn't seem to be define in the database( DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (6109, 'learn_mask_pancarte_110625_2', 16384, 25088, 'learn_mask_pancarte_110625_2', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2025, 6, 11, 13, 23, 2), datetime.datetime(2025, 6, 11, 13, 23, 2)) load thcls load THCL from format json or kwargs add thcl : 3916 in CacheModelConfig load pdts add pdt : 6109 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec no input labels no input values updating current state to 1 list_input_json: {} Current got : datou_id : 4746, datou_cur_ids : ['3689930'] with mtr_portfolio_ids : ['26718547'] and first list_photo_ids : [] new path : /proc/3036102/ 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 ! 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 14102 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13182 split_time_score_with_photo have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13182 split_time_score_with_photo is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 14090 launch_next_datou_same_portfolio is not consistent : 1 used against 0 in the step definition ! 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 1 of step 13182 doesn't seem to be define in the database( WARNING : type of input 0 of step 14090 doesn't seem to be define in the database( WARNING : type of output 2 of step 14102 doesn't seem to be define in the database( WARNING : type of input 2 of step 13182 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, split_time_score_with_photo, launch_next_datou_same_portfolio list_input_json : {} origin We have 1 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.7666997909545898 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 : 3 step1:mask_detect Wed Sep 10 13:51:29 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 : False begin detect begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 3000 l 3632 free memory gpu now : 17 wait 20 seconds l 3637 free memory gpu now : 17 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-10 13:51:52.597050: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-10 13:51:52.604403: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-10 13:51:52.605832: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd990000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-10 13:51:52.605868: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-10 13:51:52.608033: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-10 13:51:52.620758: W tensorflow/compiler/xla/service/platform_util.cc:210] unable to create StreamExecutor for CUDA:0: failed initializing StreamExecutor for CUDA device ordinal 0: Internal: failed call to cuDevicePrimaryCtxRetain: CUDA_ERROR_OUT_OF_MEMORY: out of memory; total memory reported: 11553341440 2025-09-10 13:51:52.620861: I tensorflow/compiler/jit/xla_gpu_device.cc:161] Ignoring visible XLA_GPU_JIT device. Device number is 0, reason: Internal: no supported devices found for platform CUDA 2025-09-10 13:51:52.621363: 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 2025-09-10 13:51:52.621588: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-10 13:51:52.623364: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-10 13:51:52.625049: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-10 13:51:52.625364: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-10 13:51:52.627795: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-10 13:51:52.629046: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-10 13:51:52.634059: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-10 13:51:52.635028: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-10 13:51:52.635101: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 Inside mask_sub_process Inside mask_detect Exception in mask_detect : CUDA runtime implicit initialization on GPU:0 failed. Status: out of memory we want to redo the detection max_time_sub_proc : 3600 erreur pendant la detection in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 2.40user 2.07system 0:26.92elapsed 16%CPU (0avgtext+0avgdata 400296maxresident)k 24inputs+17896outputs (10major+116356minor)pagefaults 0swaps