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) DONE and to test : checkNoCycle ! We are managing only one step so we do not consider checkConsistencyNbInputNbOutput ! We are managing only one step so we do not consider checkConsistencyTypeOutputInput ! List Step Type Loaded in datou : split_time_score over limit max, limiting to limit_max 100 list_input_json : {} origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! we have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB time to download the photos : 0.024018049240112305 About to test input to load Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 1 step1:split_time_score Tue May 13 14:30:27 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 begin split time score 2022-04-13 10:29:59 0 TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3379, 'mtr_user_id': 31, 'name': 'learn_classif_flux_maj_generique_effnet_v2_s_02062022', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'aluminium,ela,film_pedb,flux_dev,jrm,pcm,pcnc,pehd_pp,pet_clair,refus,tapis_vide', 'svm_portfolios_learning': '5515864,5515840,5515844,5515850,6244400,6237996,6237998,5515847,5515841,5515868,5515866', 'photo_hashtag_type': 4374, 'photo_desc_type': 5680, 'type_classification': 'tf_classification2', 'hashtag_id_list': '493546845,492741797,2107760237,2107760238,495916461,560181804,1284539308,2107760239,2107755846,538914404,2107748999'}] thcls : [{'id': 3513, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2_tf', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 4557, 'photo_desc_type': 5767, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('10', 219),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {1: 219} 13052025 22915454 Nombre de photos uploadées : 219 / 23040 (0%) 13052025 22915454 Nombre de photos taguées (types de déchets): 219 / 219 (100%) 13052025 22915454 Nombre de photos taguées (volume) : 219 / 219 (100%) elapsed_time : load_data_split_time_score 3.5762786865234375e-06 elapsed_time : order_list_meta_photo_and_scores 0.00010013580322265625 LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL elapsed_time : fill_and_build_computed_from_old_data 0.013152837753295898 elapsed_time : insert_dashboard_record_day_entry 0.03365969657897949 LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL Creating list_photo_by_hashtags elapsed_time : list_photo_by_hashtags 0.030392885208129883 Creating list_photo_total elapsed_time : select_descriptors 10.435333967208862 13052025 22915454 Nombre de photos avec descriptors (type 5680) : 215 / 215 (100%) ERROR : Hum hum, what can we do for different size of descriptors (ignore the difference ) : 0 vs 1280 photo_id : 1357796352 photo_id_prec : 0 0:00:00|ON:0:00:59.550465|OFF:0:00:00|ON:LL0:04:00.035256|OFF:0:00:00|ON:LL0:06:00.493988|OFF:0:00:00|ON:LL0:04:59.659413|OFF:0:00:00|ON:LL0:00:00|OFF:LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL0:05:59.701379|ON:LMissing descriptors for photos 1357831506 and 1357831548 LMissing descriptors for photos 1357831548 and 1357832927 LLLLLLL0:08:00.752124|OFF:L0:00:00|ON:LLLLLLLLLLLLLLLLLLLLLLLLLLL 13052025 Removing 39 photos because of the 'same image' condition Total on : 1440.491246 list_time_on Total off : 359.701379 list_time_off dist_desc begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 219 time used for this insertion : 0.04751729965209961 photos_removed : len 39 elapsed_time : remove_photo_duplicate 0.08423471450805664 To do, maybe not at the correct place ! ...............................L.............................................L............................L....L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L..................................L.L.L..L..........L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.L.Lforce hashtag to JRM elapsed_time : CREATE_PORT_BATCH_BY_HOUR 0.012932062149047852 NUMBER BATCH : 3 list_ponderation used : [1e-05, 1e-05, 1e-05, 1e-05, 1e-05] , list_hashtag_class_create_as_list : ['jrm'] result_one_balle_Type_JRM:{'day': '13052025', 'map_nb_amount': {0: 14, 1: 76, 2: 1, 3: 0, 4: 0}, 'map_time_amount': {0: 0, 1: 0, 2: 0, 3: 0, 4: 0}, 'duration': 839.4030909538269, 'nb_balles_papier': 0.0009200000000000018, 'begin_time_port': 'image_13052025_10_00_02_897104m0.jpg 1e-05 for time 1, id_amount 2 this amount prod time diff : 1e-05'} Production hashtag (inc