supervisely 6.73.238__py3-none-any.whl → 6.73.240__py3-none-any.whl

{supervisely-6.73.238.dist-info → supervisely-6.73.240.dist-info}/RECORD

@@ -5,7 +5,7 @@ supervisely/function_wrapper.py,sha256=R5YajTQ0GnRp2vtjwfC9hINkzQc0JiyGsu8TER373
 supervisely/sly_logger.py,sha256=LG1wTyyctyEKuCuKM2IKf_SMPH7BzkTsFdO-0tnorzg,6225
 supervisely/tiny_timer.py,sha256=hkpe_7FE6bsKL79blSs7WBaktuPavEVu67IpEPrfmjE,183
 supervisely/annotation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/annotation/annotation.py,sha256=RkAv9QO1_8KYJ_qKO_xCD5nv4Jy7g4bmim6uV2-Arek,109260
+supervisely/annotation/annotation.py,sha256=8ogjbQyAmarXg21IMCRtTWWNMdoVr0uRNXwNTmdcq5U,109308
 supervisely/annotation/annotation_transforms.py,sha256=TlVy_gUbM-XH6GbLpZPrAi6pMIGTr7Ow02iSKOSTa-I,9582
 supervisely/annotation/json_geometries_map.py,sha256=nL6AmMhFy02fw9ryBm75plKyOkDh61QdOToSuLAcz_Q,1659
 supervisely/annotation/label.py,sha256=NpHZ5o2H6dI4KiII22o2HpiLXG1yekh-bEy8WvI2Ljg,37498
@@ -25,7 +25,7 @@ supervisely/api/annotation_api.py,sha256=s9kd1G759R8YSvbDcNXrPa9xv95j1cWE1RgD6Xe
 supervisely/api/api.py,sha256=SI7DuSi2Jnj5NFS_V9aQ9Sg3CrS97Y5p1pqeeb-4Jb4,64729
 supervisely/api/app_api.py,sha256=-T4sISQ7POyR2yirf1kEWj4JaJFpJxCyRWqbf_99Jak,67036
 supervisely/api/dataset_api.py,sha256=2-SQBlgEnIN-0uvDbtPlSXr6ztBeZ3WPryhkOtpBmk4,40786
-supervisely/api/file_api.py,sha256=WMg80fxqMKOo3ai-IGON2w-IDAySPk90USoVk29JOdE,82415
+supervisely/api/file_api.py,sha256=c4iIzH2BF8-GLFLk_wc9Qz225AbHhbzH22wv5HdsGg4,83128
 supervisely/api/github_api.py,sha256=NIexNjEer9H5rf5sw2LEZd7C1WR-tK4t6IZzsgeAAwQ,623
 supervisely/api/image_annotation_tool_api.py,sha256=YcUo78jRDBJYvIjrd-Y6FJAasLta54nnxhyaGyanovA,5237
 supervisely/api/image_api.py,sha256=_wXn10tKKCcfvTiQax0O2X9lnE54nXucwQHTjA1WbRM,169172
@@ -51,7 +51,7 @@ supervisely/api/entity_annotation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR
 supervisely/api/entity_annotation/entity_annotation_api.py,sha256=K79KdDyepQv4FiNQHBj9V4-zLIemxK9WG1ig1bfBKb8,3083
 supervisely/api/entity_annotation/figure_api.py,sha256=WgeB6h8ZQsgeORXnEAq2LCCezLIMeVibetFTC1PxQM8,20896
 supervisely/api/entity_annotation/object_api.py,sha256=gbcNvN_KY6G80Me8fHKQgryc2Co7VU_kfFd1GYILZ4E,8875
-supervisely/api/entity_annotation/tag_api.py,sha256=3PQEpLZaIL_3Ds2QWfyjHZctXA1KqvVVRYbVLw7npHU,10881
+supervisely/api/entity_annotation/tag_api.py,sha256=M-28m9h8R4k9Eqo6P1S0UH8_D5kqCwAvQLYY6_Yz4oM,11161
 supervisely/api/pointcloud/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/api/pointcloud/pointcloud_annotation_api.py,sha256=_QABI38FCKBc4_VQ0B7jLOKMoRN9FFSt-w-zlEHd44s,7658
 supervisely/api/pointcloud/pointcloud_api.py,sha256=pn72znCr5hkAfgniXxfD6Vi8-HqRb1Nrf6l23-HQ7Bc,53277
@@ -705,7 +705,7 @@ supervisely/metric/metrics_tests.py,sha256=59L-J9ihYZdX5we8z_qMPZKKUxEPGTgVJqPgJ
 supervisely/metric/pixel_accuracy.py,sha256=qjtxInOTkGDwPeLUnjBdzOrVRT3V6kGGOWjBZMqMJhw,3273
 supervisely/metric/precision_recall_metric.py,sha256=4AQCkcB84mpYQS94yJ-wkG1LBuXlQf3X_tI9f67vtR8,3426
 supervisely/metric/projects_applier.py,sha256=ORtgLQHYtNi4KYsSGaGPPWiZPexTJF9IWqX_RuLRxPk,3415
-supervisely/nn/__init__.py,sha256=3TVBx23BSDsfY8iaoqBCprzL1oV_Sjcnu5rifbMl1OM,391
+supervisely/nn/__init__.py,sha256=oPFuFcvgKeMTRiklKHvJMBFaT0FMUmndS52hgF02t9M,436
 supervisely/nn/prediction_dto.py,sha256=8QQE6h_feOf3bjWtyG_PoU8FIQrr4g8PoMOyoscmqJM,1697
 supervisely/nn/task_type.py,sha256=UJvSJ4L3I08j_e6sU6Ptu7kS5p1H09rfhfoDUSZ2iys,522
 supervisely/nn/utils.py,sha256=diMo6P1FDRChLTmuxRryGvxyMenyRfUqcSi38wjQBOo,1314
@@ -721,100 +721,122 @@ supervisely/nn/artifacts/rtdetr.py,sha256=xjH3TzbHHqC06vOb_bVHTSNsWsKPwRDLN39ivQ
 supervisely/nn/artifacts/unet.py,sha256=Gn8ADfwC4F-MABVDPRY7g_ZaAIaaOAEbhhIGII-oiA4,1450
 supervisely/nn/artifacts/yolov5.py,sha256=6KDCyDlLO7AT9of1qHjCaG5mmxCv6C0p-zCk9KJ0PH4,1478
 supervisely/nn/artifacts/yolov8.py,sha256=c3MzbOTYD6RT5N4F9oZ0SWXxyonjJ6ZQfZLYUHPRZg4,1204
-supervisely/nn/benchmark/__init__.py,sha256=RxqbBx7cbzookq2DRvxYIaRofON9uxHeY5h8DqDbZq0,187
-supervisely/nn/benchmark/base_benchmark.py,sha256=LoDsT_F86Y9xztrTyfz74FmT619_rrZVUKnEtTzav0A,22755
+supervisely/nn/benchmark/__init__.py,sha256=7jDezvavJFtO9mDeB2TqW8N4sD8TsHQBPpA9RESleIQ,610
+supervisely/nn/benchmark/base_benchmark.py,sha256=8dnDPblZErN6LuoUduy7Q9XivHD-j4FXqjSJh7TqLf4,25015
+supervisely/nn/benchmark/base_evaluator.py,sha256=fxmUDsIIAahaA8yshxMA2a8klxNAOelx_pswUWVa3-o,3644
+supervisely/nn/benchmark/base_visualizer.py,sha256=APW2y-rRC6sriqn-jPRY_3oMTtP7jSviEPM2F8QCQbY,10210
 supervisely/nn/benchmark/cv_tasks.py,sha256=ShoAbuNzfMYj0Se-KOnl_-dJnrmvN6Aukxa0eq28bFw,239
-supervisely/nn/benchmark/instance_segmentation_benchmark.py,sha256=9iiWEH7KDw7ps0mQQdzIrCtCKg4umHekF3ws7jIGjmE,938
-supervisely/nn/benchmark/object_detection_benchmark.py,sha256=s1S-L952etgz-UsDPyg69AgmFfAoJXvFHhITT8zB5iw,956
-supervisely/nn/benchmark/utils.py,sha256=evcoUFPkeEW1-GvAPYp8EoOv3WAsqzaSmCY4lbLLfAQ,607
-supervisely/nn/benchmark/coco_utils/__init__.py,sha256=MKxuzzBWpRCwR8kOb5NXUK8vD-2mroJn48xd6tv9FeI,139
-supervisely/nn/benchmark/coco_utils/sly2coco.py,sha256=iudlcHNynthscH-V5qwCLk6VgIcxYrMEuAfGIjrOjZ0,6867
-supervisely/nn/benchmark/coco_utils/utils.py,sha256=J9kM_Cn4XxfsrSQ8Rx6eb1UsS65-wOybaCkI9rQDeiU,504
 supervisely/nn/benchmark/comparison/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/benchmark/comparison/model_comparison.py,sha256=HHSdMHjhR355nnxn4RqP4ew2oYvWKWQiB_enUjmBYe0,3321
 supervisely/nn/benchmark/comparison/detection_visualization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/comparison/detection_visualization/text_templates.py,sha256=mkv0lqlnpp-Dtlqk7G5UmUbs6hfStbxEL-1RGOw626s,28357
+supervisely/nn/benchmark/comparison/detection_visualization/text_templates.py,sha256=lBqcNsyOX04R2jL6Efu43xB2aHC1qx28Kw27DLuk66o,28336
 supervisely/nn/benchmark/comparison/detection_visualization/visualizer.py,sha256=JuLtDL37nY5pYZW2aHq4exqyqwRcWvyC9_yO45NxoeU,12869
 supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/__init__.py,sha256=L01ExPfYQsAUVKeDyR7sybDo4lqW152q8ubs4mYMi80,1126
 supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/avg_precision_by_class.py,sha256=0_2sUoS-9e7ZSpTCJBepwbZHYQiE9mJtWlwZMBmM1Lk,4634
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/calibration_score.py,sha256=VZ9SG4v7Cb2Yk9RT5hBTKzjOwvVSAX8UKSlUtUJmXks,7641
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/explore_predicttions.py,sha256=Fym-9QX4OKSGnLkV_12ov2dFHvNvTev3wJXoSbWDt1I,5005
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/localization_accuracy.py,sha256=6O-ddSIcoG5jYWZvFShAYNMxwczzUgrmWfW5ywMWibU,5391
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/outcome_counts.py,sha256=h1qhI-GDDqW1B-y30Vh2ZuJRh60xOk2Tujr1pMmi2i4,13136
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/overview.py,sha256=gHiUweroxt69fVf7eOu-lgCzkxYf6aO2lnPidR_MwEY,9432
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/pr_curve.py,sha256=eiQ1uQbYo6idjVpW4vgnhwQ1P_pVZ6fx4zLuqAy2LNI,4846
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/precision_recal_f1.py,sha256=HXpcgPDot18NnWV-Xz30zqr7Wg1RGEVLYFYz2N5TEsI,11460
-supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/speedtest.py,sha256=FyIG-1iNNd4NyDsJkSGdFJmcrA7vMrWH15UbC8jVs8M,10583
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/calibration_score.py,sha256=ut6xDtDSjvgZaxdlwni3R2KL41_Ze0WPCFy0IBd_oNY,7653
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/explore_predicttions.py,sha256=oADcHrid3GcvZVwM5UHHgIxJswpTBQBB4Ih3RvYXdGA,6392
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/localization_accuracy.py,sha256=-fAvX4WPMrEoam170ROqAeeYg8pfobJBW6TXZMHhafo,5397
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/outcome_counts.py,sha256=QlMha7kdqJl_hshC1ZAuDgi0afZHwp8SyMGRpbtXT3s,13201
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/overview.py,sha256=TZen3vC1TCOEm54vZbyKNkZtHb0mSvvSTzQnWx4sJu0,9592
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/pr_curve.py,sha256=vBqkfdDmtlOG23CtFD9MYXrOzcQnLXsMmOF7sNQOdOc,4852
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/precision_recal_f1.py,sha256=9k49G-SRxT2CeE0LZtFVqV4e0uX_YqjgxCyvRPRABS4,11496
+supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/speedtest.py,sha256=0NtSB-SHkw4ynRaIl8Mm0ed-h6bFr9L-ZKxnzXJbn70,10658
 supervisely/nn/benchmark/comparison/detection_visualization/vis_metrics/vis_metric.py,sha256=sRIf1q9a2ulTgm2xEZ3IMOsse8ZljbMake0_VGCnbbU,587
-supervisely/nn/benchmark/evaluation/__init__.py,sha256=1NGV_xEGe9lyPdE5gJ8AASKzm2WyZ_jKlh9WVvCQIaY,287
-supervisely/nn/benchmark/evaluation/base_evaluator.py,sha256=htei2QGHsx-1DO16j-lUjflmUFpfSIv0drhGfe60qAU,1995
-supervisely/nn/benchmark/evaluation/instance_segmentation_evaluator.py,sha256=p2VC4WXB2RQlmeRt14u74QTXSOwhkyQPCznw7Kqe32k,3773
-supervisely/nn/benchmark/evaluation/object_detection_evaluator.py,sha256=0Sp0h9kNQUQYVRL3WrV9Vm7OniJPMYriEFbwcCejOBs,3615
-supervisely/nn/benchmark/evaluation/coco/__init__.py,sha256=l6dFxp9aenywosQzQkIaDEI1p-DDQ63OgJJXxSVB4Mk,172
-supervisely/nn/benchmark/evaluation/coco/calculate_metrics.py,sha256=Pe5_bXJ57343PQ0TuYEkCMNUyp-YTyIXnPXUESuXQBk,11430
-supervisely/nn/benchmark/evaluation/coco/evaluation_params.yaml,sha256=POzpiaxnxuwAPSNQOGgjoUPfsk6Lf5hb9GLHwltWY5Y,94
-supervisely/nn/benchmark/evaluation/coco/metric_provider.py,sha256=4_-RJNtpyEiUfY8NexeXzCjScQvB6xn07u_M9IVs9ak,19951
-supervisely/nn/benchmark/evaluation/coco/metrics.py,sha256=oyictdJ7rRDUkaVvHoxntywW5zZweS8pIJ1bN6JgXtE,2420
+supervisely/nn/benchmark/instance_segmentation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/instance_segmentation/benchmark.py,sha256=_KeKEppSCDi1g9Wgo3klp5XwS8FSFt2S4mkanYrN4Rc,1170
+supervisely/nn/benchmark/instance_segmentation/evaluation_params.yaml,sha256=POzpiaxnxuwAPSNQOGgjoUPfsk6Lf5hb9GLHwltWY5Y,94
+supervisely/nn/benchmark/instance_segmentation/evaluator.py,sha256=Spmo4a5LMFe5zW3s0mS-pbVKAgb27Wlxuj91Z3YXqTo,2305
+supervisely/nn/benchmark/instance_segmentation/text_templates.py,sha256=sGiGnpIyuOP35f4NoDT0BWNmscsx_T1XZ_igGvCkkBg,25481
+supervisely/nn/benchmark/instance_segmentation/visualizer.py,sha256=8NscOKy7JK4AG-Czu3SM0qJQXLDfKD9URdG1d4nz89E,564
+supervisely/nn/benchmark/object_detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/object_detection/base_vis_metric.py,sha256=XjUnFCnCMYLrpjojIOwiRNaSsSLYpozTHWfwLkaCd5U,1612
+supervisely/nn/benchmark/object_detection/benchmark.py,sha256=SXdCGFH2KWl5UYDZBdx-J0P15GyHDs0aQOR7ZudBEBw,1085
+supervisely/nn/benchmark/object_detection/evaluation_params.yaml,sha256=POzpiaxnxuwAPSNQOGgjoUPfsk6Lf5hb9GLHwltWY5Y,94
+supervisely/nn/benchmark/object_detection/evaluator.py,sha256=g-QgWzbBLGzBTrv1jonNYCKkYx-M5zSkzs0KkuIVrzg,5667
+supervisely/nn/benchmark/object_detection/metric_provider.py,sha256=NWN1yWK0YIE_Fz24OnhwylGlkzxJKrLP8FLVf3-L8ts,19930
+supervisely/nn/benchmark/object_detection/text_templates.py,sha256=wv6BkcrfdEKldbXtz4ljkbENIIOdeiUr79U4iRgUx6A,25727
+supervisely/nn/benchmark/object_detection/visualizer.py,sha256=drqndVZT-APwwTiDuMWeYXpnHF89rDsIEspneWqYSSE,31838
+supervisely/nn/benchmark/object_detection/vis_metrics/__init__.py,sha256=AXCLHEySEdR-B-5sfDoWBmmOLBVlyW2U_xr8Ta42sQI,2096
+supervisely/nn/benchmark/object_detection/vis_metrics/confidence_distribution.py,sha256=OlwkPgzEQ-RegcLZHVUVOL0n6I_2iayPVpAIie4y2O8,3615
+supervisely/nn/benchmark/object_detection/vis_metrics/confidence_score.py,sha256=r_saaZI4WB7C7ykNb1obmf8kEOkphLA4pInDoS6dXXU,4005
+supervisely/nn/benchmark/object_detection/vis_metrics/confusion_matrix.py,sha256=2PJUt0-njRpzN7XBGjkSt9kkh5tDPuv_Sne-2v8DWHc,3731
+supervisely/nn/benchmark/object_detection/vis_metrics/explore_predictions.py,sha256=wIYfq3izM2XNJHr56h3j5XhuU8W8Y3wO_RKAwxntQs4,4855
+supervisely/nn/benchmark/object_detection/vis_metrics/f1_score_at_different_iou.py,sha256=6y2Kx-R_t4SdJkdWNyZQ6TGjCC-u6KhXb4cCno4GuTk,2882
+supervisely/nn/benchmark/object_detection/vis_metrics/frequently_confused.py,sha256=7rObk7WNsfwK7xBWl3aOxcn0uD48njEc04fQIPHc3_4,4678
+supervisely/nn/benchmark/object_detection/vis_metrics/iou_distribution.py,sha256=lv4Bk8W4X8ZhvQKyMXI46d240PNlMFx1hdji_aoTS50,3601
+supervisely/nn/benchmark/object_detection/vis_metrics/key_metrics.py,sha256=Z8qArtjqjjRW5Z4mBuanzK3b4LLfH6NgNbO2Lt0kXyo,4316
+supervisely/nn/benchmark/object_detection/vis_metrics/model_predictions.py,sha256=gsGDsesiwOcqeFvHr33b4PSJNw6MoA5brO-qRydRtsA,5944
+supervisely/nn/benchmark/object_detection/vis_metrics/outcome_counts.py,sha256=HuTgisYmXCSUeF5WOahy-uaCdvRLsNzg28BDrZ-5hww,7161
+supervisely/nn/benchmark/object_detection/vis_metrics/outcome_counts_per_class.py,sha256=GBq0KlPka5z4cxHcKCe2eVOI_h3qlWUqGCyhYs6mjrk,6825
+supervisely/nn/benchmark/object_detection/vis_metrics/overview.py,sha256=2ToNTbgzQA6EGdtGFPqd9jHzcLCCzpIL1FS7jwstQLg,5131
+supervisely/nn/benchmark/object_detection/vis_metrics/pr_curve.py,sha256=EeZmyNlTVQLQ-0wIDGdvFmRkahJBBiOKSmWiAJ8Bfks,3478
+supervisely/nn/benchmark/object_detection/vis_metrics/pr_curve_by_class.py,sha256=Bl_buVvH8SVqwsc4DcHnojMOqpwTnRgXFt9yw_Y1BR0,1607
+supervisely/nn/benchmark/object_detection/vis_metrics/precision.py,sha256=473bhBQ31-kFoyNsDNTs4GPwOiexSskxKPP8AP_nHDg,2605
+supervisely/nn/benchmark/object_detection/vis_metrics/precision_avg_per_class.py,sha256=X-hyf7OP7hzQzI5Yb2yDU536hxYQLvxcnVyYa3x27XA,2076
+supervisely/nn/benchmark/object_detection/vis_metrics/recall.py,sha256=VQZqrlYLUbrFV7ugp2Bo1SIaKCs_jA7qrodatzB4_rE,2483
+supervisely/nn/benchmark/object_detection/vis_metrics/recall_vs_precision.py,sha256=md9pj3V5hL7GE92ehVhhCz3uEWd3HsqtGIfyIZPas68,1937
+supervisely/nn/benchmark/object_detection/vis_metrics/reliability_diagram.py,sha256=_8ie3dPfwOyNCg-YhqO5jFW6kubCfQC2Obn9QSZFVeQ,3615
+supervisely/nn/benchmark/object_detection/vis_metrics/speedtest.py,sha256=uAYu42WUcQCBdfm-PZxOPAGLDsPlcnDJL7PCXDRStbY,5449
+supervisely/nn/benchmark/semantic_segmentation/__init__.py,sha256=Hx5bFhRZq8BXvN_ATAxlrhsxWcVy32pT4xIkqa-16RM,326
+supervisely/nn/benchmark/semantic_segmentation/base_vis_metric.py,sha256=mwGjRUTPrIj56WHsxNW_4fcZM0uw1xm6B5wh25FijyQ,1788
+supervisely/nn/benchmark/semantic_segmentation/benchmark.py,sha256=8rnU6I94q0GUdXWwluZu0_Sac_eU2-Az133tHF1dA3U,1202
+supervisely/nn/benchmark/semantic_segmentation/evaluation_params.yaml,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/semantic_segmentation/evaluator.py,sha256=SjFGBju1rghXeBkOZjnaCnyIo04C6aEb1ltDKvR2ME4,6158
+supervisely/nn/benchmark/semantic_segmentation/metric_provider.py,sha256=KvbiiEqNOuTSwp4IfV6GC8azYFb-9OZ6ZrYV7pw4KEc,6491
+supervisely/nn/benchmark/semantic_segmentation/text_templates.py,sha256=fYJQeO75LTMzbz0KG01TPGYrMatEuHAF9cnPWolUsoQ,8585
+supervisely/nn/benchmark/semantic_segmentation/visualizer.py,sha256=qbpz6b3aUhvByTFvE44u0X7DdTRgaITTBYD4TWIysI4,13102
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/acknowledgement.py,sha256=Lm82x8AIMKv1WqmqA0W9fugSlQ_JrP9dwYYYReZmhvI,440
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/classwise_error_analysis.py,sha256=0bmL43a4cqw3grFoG68NN8Y1fkRpHBIRJptcxMor-78,1884
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/confusion_matrix.py,sha256=xpvicxgwDaih-64VSAsxdNvoFxeA_iaUGOK9gpvNyuQ,3233
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/explore_predictions.py,sha256=QVtcGQv4S8W7jLANUsvuJaPP-OrUQ_LB2oEpjpLBecw,2936
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/frequently_confused.py,sha256=SyVgMD66EFLfgrClb5RCJjLhgRfTYqGsUORPYIuSe58,3697
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/iou_eou.py,sha256=IdUho3712dDLyVsgR01aNSQBcraPzYwpJmTc9AB0Txw,1401
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/key_metrics.py,sha256=vJb30-aQ-ffUTo_vX4ZQL8wjN0VYI6jwR2ILH5jXGDw,1886
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/model_predictions.py,sha256=1ysQLOmYJvrCPdqkXhRb5p_TyyXWdAVBDXoCJpfZrNo,3807
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/overview.py,sha256=3E8TqjTWkhFFvcl0v0SjVz7muIkaZRfsG6fiW76ooqE,4851
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/renormalized_error_ou.py,sha256=w4oqirf_o7uz0fwaapaFR0ByjCBSEfMv--ZgEZTkuFQ,1575
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/speedtest.py,sha256=0UP_HReIciHQyU6sOXnWhAzyVBoGznV7ZHF8m4vEVX0,5941
+supervisely/nn/benchmark/semantic_segmentation/vis_metrics/vis_texts.py,sha256=rRdYZxmhQX4T3RsXJVGp34NMZPz8jUHtVvBN5BpPJ5I,603
+supervisely/nn/benchmark/utils/__init__.py,sha256=JHT73gWdwgLJKTiCpDdwggm1t_EWB0JCC90-zD7reXM,741
+supervisely/nn/benchmark/utils/detection/__init__.py,sha256=L3QKGuKUlR2N_QFRTRsa6gfLDbksIaFMYO0Hukxxy1U,172
+supervisely/nn/benchmark/utils/detection/calculate_metrics.py,sha256=DyGNBhnifAFZL8-OwRrrFritzLKJeCcEwEZsLXPd148,11446
+supervisely/nn/benchmark/utils/detection/metric_provider.py,sha256=cgF6uzF7XOvU2CpxyU7zuK1HH6hhNiIV3vQc8MAzwMU,19934
+supervisely/nn/benchmark/utils/detection/metrics.py,sha256=oyictdJ7rRDUkaVvHoxntywW5zZweS8pIJ1bN6JgXtE,2420
+supervisely/nn/benchmark/utils/detection/sly2coco.py,sha256=0O2LSCU5zIX34mD4hZIv8O3-j6LwnB0DqhiVPAiosO8,6883
+supervisely/nn/benchmark/utils/detection/utlis.py,sha256=pDmlq_lb90L1D1avsTPlqd4-t19UlERrWyIzSNU3K60,902
+supervisely/nn/benchmark/utils/semantic_segmentation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/utils/semantic_segmentation/calculate_metrics.py,sha256=4ifC5r_Q880yIr8gWnjEzwKbS0vizMWqSF4XeyaMvh0,924
+supervisely/nn/benchmark/utils/semantic_segmentation/evaluator.py,sha256=R1U_mnOiUUH6P87xiKalYqMpj1uGCJKuOBcsTmVHawY,32894
+supervisely/nn/benchmark/utils/semantic_segmentation/loader.py,sha256=_5ZZ7Nkd8WWYJnKwc1Dx3bEPS_1R84gG_hQc0w0TXWw,1957
+supervisely/nn/benchmark/utils/semantic_segmentation/utils.py,sha256=nV9T7PCUxOdipFIBPrpdwLJXs0GJNp_Eft2MJmrKJRM,3787
 supervisely/nn/benchmark/visualization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/evaluation_result.py,sha256=TT4ADr6uSOKzohWpbLsamfHnbsNMMcyWSVSWgoj8TVY,9835
+supervisely/nn/benchmark/visualization/evaluation_result.py,sha256=733HJL4rJa5XqCJydW9vSyaepvpHzym9wQsw1wFEgeI,10251
 supervisely/nn/benchmark/visualization/renderer.py,sha256=qxWUYu2glTqksxI5UG08nwDmZA4A2bfGb1wk9DaDct8,3340
 supervisely/nn/benchmark/visualization/report_template.html,sha256=tylBK5Bb2cqKACK1GZUKyIjPS9yHQFHAS-QeEEwhqTE,2172
-supervisely/nn/benchmark/visualization/vis_click_data.py,sha256=4QdBZqJmmPYdcB7x565zOtXhDFRyXIB4tpu0V-_otoc,3724
-supervisely/nn/benchmark/visualization/vis_metric_base.py,sha256=hXnbGAijnZ700GuzfvaHBxU5elQR0wXkBUNbmcSWCno,13941
-supervisely/nn/benchmark/visualization/vis_templates.py,sha256=Vy019K8G8oJ9vN35tvsSjYA21xdldqIP-BALGEuy_eM,10169
-supervisely/nn/benchmark/visualization/vis_widgets.py,sha256=oavMM2Z-05Hp_Fj086NgXAqDq2KPAqXfT-nJb5qlDsg,4103
-supervisely/nn/benchmark/visualization/visualizer.py,sha256=1VhcuM44LIZv6RHzsSpU9K-Yq3MqAhuwO2JGuWN5Ots,32149
-supervisely/nn/benchmark/visualization/inference_speed/__init__.py,sha256=6Nahwt9R61_Jc1eWupXa70CgyRQ7tbUeiDWR26017rY,554
-supervisely/nn/benchmark/visualization/inference_speed/speedtest_batch.py,sha256=73gbXs1uTfxxWH-UCJdR72m-48jMD5qVyMyolf5jNoc,6140
-supervisely/nn/benchmark/visualization/inference_speed/speedtest_intro.py,sha256=ivUVriKyhx9ZtwVSqrAkUqq1SJGYYxNLwLQR1UgE4aM,900
-supervisely/nn/benchmark/visualization/inference_speed/speedtest_overview.py,sha256=QLgiiHJzmasnNmn6OGWfLef01gLOiM84uVBK5P8c954,4887
-supervisely/nn/benchmark/visualization/inference_speed/speedtest_real_time.py,sha256=bVpNS3YBP0TGsqE_XQBuFMJI5ybDM0RZpEzFyT7cbkA,2157
-supervisely/nn/benchmark/visualization/text_templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/text_templates/inference_speed_text.py,sha256=XGeBrbP-ROyKYbqYZzA281_IG45Ygu9NKyqG2I3o5TU,1124
-supervisely/nn/benchmark/visualization/text_templates/instance_segmentation_text.py,sha256=ud_XqN3q8nbpAvk3JvW_8LNcmnkq7B-MuLgILgSVeJA,25116
-supervisely/nn/benchmark/visualization/text_templates/object_detection_text.py,sha256=jKHeKZGwEP1rnKpKHpf9x5iP9L8JaFMkvnFcayxvgeI,24508
-supervisely/nn/benchmark/visualization/vis_metrics/__init__.py,sha256=Qrd9NMgFUQ1nbEy4NEu59RXR4OmVaBdK_iLOGpwVRCA,2249
-supervisely/nn/benchmark/visualization/vis_metrics/classwise_error_analysis.py,sha256=8S_XYSA_qyVWAEnvebdjuw9ktJScDHgTVvZRfh-bvpc,1841
-supervisely/nn/benchmark/visualization/vis_metrics/confidence_distribution.py,sha256=m-z0-jPn3dd_X-w49Zjkb4qEEP6Rw6fVpSjgSuJoeRw,3794
-supervisely/nn/benchmark/visualization/vis_metrics/confidence_score.py,sha256=F38WSVF2a2ePV7DWfYdxDlSjM68NvjPMccfaTQWg0uI,3356
-supervisely/nn/benchmark/visualization/vis_metrics/confusion_matrix.py,sha256=SFDRpoJX-IJYv-SoCXOyhXZTpVUm6G1IYCe15Nei9Uc,3362
-supervisely/nn/benchmark/visualization/vis_metrics/explorer_grid.py,sha256=-TmGMWr6bHZd80TBGk3S_qdDQ-xlAL-zczAYw8h9vtU,5738
-supervisely/nn/benchmark/visualization/vis_metrics/f1_score_at_different_iou.py,sha256=QbHUT0-beBs0z8anbma1MS6iNEG89CmL6iSj8-ejnlc,3158
-supervisely/nn/benchmark/visualization/vis_metrics/frequently_confused.py,sha256=2lhwqaXdIEXhFSaqBYcJjRLp_OgBTEYxajYib0v4qRQ,3992
-supervisely/nn/benchmark/visualization/vis_metrics/iou_distribution.py,sha256=Kir2F3piCBf-xKhoQzVXbo38zyrLLhOr3bYay90H1-g,3015
-supervisely/nn/benchmark/visualization/vis_metrics/model_predictions.py,sha256=VmsvHwG1YJ6mMlU676cyNRXkVOcNbSvKwyVpxs4SMis,6108
-supervisely/nn/benchmark/visualization/vis_metrics/outcome_counts.py,sha256=rsm_hdE0pYCHY-5v0pjDIid71y2tPbzYbmH2Qw-RS-4,3983
-supervisely/nn/benchmark/visualization/vis_metrics/outcome_counts_per_class.py,sha256=lSb2-jfplyERIUCi8_6P9aq6C77JGOKOJK20J824sEE,5623
-supervisely/nn/benchmark/visualization/vis_metrics/overall_error_analysis.py,sha256=YHfueea2EkUgNGP4FCyKyCaCtCwaYeYNJ3WwfF-Hzi4,3553
-supervisely/nn/benchmark/visualization/vis_metrics/overview.py,sha256=V-uNrtNhR5idywyfFSNOA4zFesTf5d6i2g8MNtLOhIw,6997
-supervisely/nn/benchmark/visualization/vis_metrics/percision_avg_per_class.py,sha256=mm8IVM90EoIC_9GsiM-Jyhh6jPqQcHMo788VAvRAzMY,1877
-supervisely/nn/benchmark/visualization/vis_metrics/pr_curve.py,sha256=4-AwEQk1ywuW4zXO_EXo7_aFMjenwhnLlGX2PWqiu0k,3574
-supervisely/nn/benchmark/visualization/vis_metrics/pr_curve_by_class.py,sha256=9Uuibo38HVGPChPbCW8i3cMYdb6-NFlys1TBisp5zOU,1442
-supervisely/nn/benchmark/visualization/vis_metrics/precision.py,sha256=_ATnCkson-tSOv3xp7LI7BmwzIax75zuKs7VoeBZ_ds,2156
-supervisely/nn/benchmark/visualization/vis_metrics/recall.py,sha256=trRMw8ziWMaDp5cmJuwFaJ6aO_rfsTbCYb9LMdr9D_Q,2078
-supervisely/nn/benchmark/visualization/vis_metrics/recall_vs_precision.py,sha256=RuN3tQA3Zt5MmCha8T0WgWDIvzURjsqfL4ap_LYqN-Y,1859
-supervisely/nn/benchmark/visualization/vis_metrics/reliability_diagram.py,sha256=Vxta2s0RTTcV0GCcMiF8CykCtZYryLTwGjW9vVUrK3I,3107
-supervisely/nn/benchmark/visualization/vis_metrics/what_is.py,sha256=MDnYR-o7Mj-YE1Jwu9EcLUEPcu6rLknRx7LvV4nnUBo,842
-supervisely/nn/benchmark/visualization/widgets/__init__.py,sha256=pH-S6KlLE12uFl3KUHTyxvgd75NhI229SZ96sh-buJI,840
-supervisely/nn/benchmark/visualization/widgets/widget.py,sha256=X96Gan8xlAuhKJMW_twFXMXbIWjS0idL5abcvircSA0,702
+supervisely/nn/benchmark/visualization/vis_click_data.py,sha256=hBeVepHngTGVHK3MiWe8qZY87taifxnoUXq22W2xaqo,3724
+supervisely/nn/benchmark/visualization/widgets/__init__.py,sha256=UovmhwLH4Au81JFrFz0NwPasaIqPEI-zXN-JntTc2FU,949
+supervisely/nn/benchmark/visualization/widgets/widget.py,sha256=1cpfyaZjug8ZQIRR5SB4BgkSxP3BMwkYFRWH36U1eF0,818
 supervisely/nn/benchmark/visualization/widgets/chart/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/widgets/chart/chart.py,sha256=BhGQgG5t0mIuGK3sU4_xwoTZqkQOBXbFtJaoHqQ5L8I,2288
+supervisely/nn/benchmark/visualization/widgets/chart/chart.py,sha256=wBq0HaSixzxzlosGys2jFGLfKuFIld6p3tLWD0TF_Jo,2553
 supervisely/nn/benchmark/visualization/widgets/chart/template.html,sha256=X3jm8P3BngF_XCV9NOypOsrGH0NuesUdxvhO3tZs9yQ,637
 supervisely/nn/benchmark/visualization/widgets/collapse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/benchmark/visualization/widgets/collapse/collapse.py,sha256=iRtf5kThl5zzzYwBbA0WepAroK_LRgNJBcP0TvDHwEo,916
 supervisely/nn/benchmark/visualization/widgets/container/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/benchmark/visualization/widgets/container/container.py,sha256=ZV7auhFLZDsEVv8FoAKygiGKCeFjDG078Wmcpx7U6-w,1802
 supervisely/nn/benchmark/visualization/widgets/gallery/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/widgets/gallery/gallery.py,sha256=KRpfqfSFwWNabcIdFzT4huzWLzmpFiQVxgx8-Vp6vKM,4504
-supervisely/nn/benchmark/visualization/widgets/gallery/template.html,sha256=7UPZexDEVTzQxORXlMDidl4RWb9SSh8kLxEiE2ySC6o,1882
+supervisely/nn/benchmark/visualization/widgets/gallery/gallery.py,sha256=Lid8sZexDfgoWDupCWOiHowVnKn687F7S1fnDomrtfA,5578
+supervisely/nn/benchmark/visualization/widgets/gallery/template.html,sha256=GuxIVCuqUN41Pe-F11RrrMZxomkWld2UM6j5U8RL2UU,2003
 supervisely/nn/benchmark/visualization/widgets/markdown/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/widgets/markdown/markdown.py,sha256=jQOHBgLFZROUPYC1JxlHOjp06tmpLNSuNzQZ7604TmY,1531
+supervisely/nn/benchmark/visualization/widgets/markdown/markdown.py,sha256=j0e3lVZJZVrFrtAxpNTOlmUpsjeqoS9yJHR5m8zJMiI,1528
 supervisely/nn/benchmark/visualization/widgets/notification/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/widgets/notification/notification.py,sha256=PIVGiIlpkLMJ40anqSmXFkXbAK6umuZNJCPeT5NnFac,1054
+supervisely/nn/benchmark/visualization/widgets/notification/notification.py,sha256=J-n_RXRl6o67-qbCHp-l-_Kw1prkTmfeigwxx7tRQLI,1183
+supervisely/nn/benchmark/visualization/widgets/radio_group/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/benchmark/visualization/widgets/radio_group/radio_group.py,sha256=NtX5LB1kRbYC8KLVOUqiZECt7jvrYfHpaFqAXcTRCCg,925
 supervisely/nn/benchmark/visualization/widgets/sidebar/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/benchmark/visualization/widgets/sidebar/sidebar.py,sha256=tKPURRSF6_zZReG06MJ5a1nrRWBNtCDFKGm_eEAOp8I,2084
 supervisely/nn/benchmark/visualization/widgets/table/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/benchmark/visualization/widgets/table/table.py,sha256=YiCpt-mdINJnNBWsUTPkRR_9w09Ne2Y0n93DY8vsE8I,4090
+supervisely/nn/benchmark/visualization/widgets/table/table.py,sha256=atmDnF1Af6qLQBUjLhK18RMDKAYlxnsuVHMSEa5a-e8,4319
 supervisely/nn/inference/__init__.py,sha256=mtEci4Puu-fRXDnGn8RP47o97rv3VTE0hjbYO34Zwqg,1622
 supervisely/nn/inference/cache.py,sha256=KvzCgMbEBLdiJAxJDLicIPKAlYb52P9_kpNPWfiVY8Y,28194
 supervisely/nn/inference/inference.py,sha256=CmQe6QnhZuUV128jcIp2YKsgeggAtmc1NL7PdFnc_hw,116997
@@ -935,7 +957,7 @@ supervisely/project/data_version.py,sha256=nknaWJSUCwoDyNG9_d1KA-GjzidhV9zd9Cn8c
 supervisely/project/download.py,sha256=qonvHBiKX-leHW9qWJdyBqFNmpI2_t9s54e68h9orq0,23687
 supervisely/project/pointcloud_episode_project.py,sha256=fcaFAaHVn_VvdiIfHl4IyEFE5-Q3VFGfo7_YoxEma0I,41341
 supervisely/project/pointcloud_project.py,sha256=Y8Xhi6Hg-KyztwFncezuDfKTt2FILss96EU_LdXzmrA,49172
-supervisely/project/project.py,sha256=byf0WUxIvfoqFwq57Yea0hnljHWVrZMYMH8cGCH_rCM,181356
+supervisely/project/project.py,sha256=UB0DdouhKsER4lhW8BlLRfzf_ZzuUv0lKRKUpA46GiM,182025
 supervisely/project/project_meta.py,sha256=26s8IiHC5Pg8B1AQi6_CrsWteioJP2in00cRNe8QlW0,51423
 supervisely/project/project_settings.py,sha256=NLThzU_DCynOK6hkHhVdFyezwprn9UqlnrLDe_3qhkY,9347
 supervisely/project/project_type.py,sha256=_3RqW2CnDBKFOvSIrQT1RJQaiHirs34_jiQS8CkwCpo,530
@@ -997,9 +1019,9 @@ supervisely/worker_proto/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZ
 supervisely/worker_proto/worker_api_pb2.py,sha256=VQfi5JRBHs2pFCK1snec3JECgGnua3Xjqw_-b3aFxuM,59142
 supervisely/worker_proto/worker_api_pb2_grpc.py,sha256=3BwQXOaP9qpdi0Dt9EKG--Lm8KGN0C5AgmUfRv77_Jk,28940
 supervisely_lib/__init__.py,sha256=7-3QnN8Zf0wj8NCr2oJmqoQWMKKPKTECvjH9pd2S5vY,159
-supervisely-6.73.238.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-supervisely-6.73.238.dist-info/METADATA,sha256=j1-Fhh_Bn7kB7RBO05jQFsdygCHuK041cngXQYcClig,33157
-supervisely-6.73.238.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-supervisely-6.73.238.dist-info/entry_points.txt,sha256=U96-5Hxrp2ApRjnCoUiUhWMqijqh8zLR03sEhWtAcms,102
-supervisely-6.73.238.dist-info/top_level.txt,sha256=kcFVwb7SXtfqZifrZaSE3owHExX4gcNYe7Q2uoby084,28
-supervisely-6.73.238.dist-info/RECORD,,
+supervisely-6.73.240.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+supervisely-6.73.240.dist-info/METADATA,sha256=AIoj0IdizC_kg3QG2ExZsXz19mHqbh7qFPZF7OPO_nY,33277
+supervisely-6.73.240.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+supervisely-6.73.240.dist-info/entry_points.txt,sha256=U96-5Hxrp2ApRjnCoUiUhWMqijqh8zLR03sEhWtAcms,102
+supervisely-6.73.240.dist-info/top_level.txt,sha256=kcFVwb7SXtfqZifrZaSE3owHExX4gcNYe7Q2uoby084,28
+supervisely-6.73.240.dist-info/RECORD,,

supervisely/nn/benchmark/coco_utils/__init__.py

@@ -1,2 +0,0 @@
-from supervisely.nn.benchmark.coco_utils.sly2coco import sly2coco
-from supervisely.nn.benchmark.coco_utils.utils import read_coco_datasets

supervisely/nn/benchmark/evaluation/__init__.py

@@ -1,3 +0,0 @@
-from supervisely.nn.benchmark.evaluation.base_evaluator import BaseEvaluator
-from supervisely.nn.benchmark.evaluation.object_detection_evaluator import ObjectDetectionEvaluator
-from supervisely.nn.benchmark.evaluation.instance_segmentation_evaluator import InstanceSegmentationEvaluator

supervisely/nn/benchmark/evaluation/base_evaluator.py

@@ -1,64 +0,0 @@
-import os
-import pickle
-from typing import List, Optional, Union
-
-import yaml
-
-from supervisely.app.widgets import SlyTqdm
-from supervisely.task.progress import tqdm_sly
-
-
-class BaseEvaluator:
-    EVALUATION_PARAMS_YAML_PATH: str = None
-
-    def __init__(
-        self,
-        gt_project_path: str,
-        dt_project_path: str,
-        result_dir: str = "./evaluation",
-        progress: Optional[SlyTqdm] = None,
-        items_count: Optional[int] = None,  # TODO: is it needed?
-        classes_whitelist: Optional[List[str]] = None,
-        evaluation_params: Optional[dict] = None,
-    ):
-        self.gt_project_path = gt_project_path
-        self.dt_project_path = dt_project_path
-        self.result_dir = result_dir
-        self.total_items = items_count
-        self.pbar = progress or tqdm_sly
-        os.makedirs(result_dir, exist_ok=True)
-        self.classes_whitelist = classes_whitelist
-
-        if evaluation_params is None:
-            evaluation_params = self._get_default_evaluation_params()
-        self.evaluation_params = evaluation_params
-        if self.evaluation_params:
-            self.validate_evaluation_params(self.evaluation_params)
-
-    def evaluate(self):
-        raise NotImplementedError()
-
-    def get_result_dir(self) -> str:
-        return self.result_dir
-
-    @classmethod
-    def load_yaml_evaluation_params(cls) -> Union[str, None]:
-        if cls.EVALUATION_PARAMS_YAML_PATH is None:
-            return None
-        with open(cls.EVALUATION_PARAMS_YAML_PATH, "r") as f:
-            return f.read()
-
-    @classmethod
-    def validate_evaluation_params(cls, evaluation_params: dict) -> None:
-        pass
-
-    @classmethod
-    def _get_default_evaluation_params(cls) -> dict:
-        if cls.EVALUATION_PARAMS_YAML_PATH is None:
-            return {}
-        else:
-            return yaml.safe_load(cls.load_yaml_evaluation_params())
-
-    def _dump_pickle(self, data, file_path):
-        with open(file_path, "wb") as f:
-            pickle.dump(data, f)

supervisely/nn/benchmark/evaluation/coco/__init__.py

@@ -1,2 +0,0 @@
-from supervisely.nn.benchmark.evaluation.coco.calculate_metrics import calculate_metrics
-from supervisely.nn.benchmark.evaluation.coco.metric_provider import MetricProvider

supervisely/nn/benchmark/evaluation/instance_segmentation_evaluator.py

@@ -1,88 +0,0 @@
-import os
-
-from supervisely.io.json import dump_json_file
-from supervisely.nn.benchmark.coco_utils import read_coco_datasets, sly2coco
-from supervisely.nn.benchmark.evaluation import BaseEvaluator
-from supervisely.nn.benchmark.evaluation.coco import calculate_metrics
-from pathlib import Path
-
-
-class InstanceSegmentationEvaluator(BaseEvaluator):
-    EVALUATION_PARAMS_YAML_PATH = f"{Path(__file__).parent}/coco/evaluation_params.yaml"
-
-    def evaluate(self):
-        try:
-            self.cocoGt_json, self.cocoDt_json = self._convert_to_coco()
-        except AssertionError as e:
-            raise ValueError(
-                f"{e}. Please make sure that your GT and DT projects are correct. "
-                "If GT project has nested datasets and DT project was crated with NN app, "
-                "try to use newer version of NN app."
-            )
-
-        self._dump_datasets()
-        self.cocoGt, self.cocoDt = read_coco_datasets(self.cocoGt_json, self.cocoDt_json)
-        with self.pbar(message="Evaluation: Calculating metrics", total=5) as p:
-            self.eval_data = calculate_metrics(
-                self.cocoGt,
-                self.cocoDt,
-                iouType="segm",
-                progress_cb=p.update,
-                evaluation_params=self.evaluation_params,
-            )
-        self._dump_eval_results()
-
-    @classmethod
-    def validate_evaluation_params(cls, evaluation_params: dict) -> None:
-        iou_threshold = evaluation_params.get("iou_threshold")
-        if iou_threshold is not None:
-            assert iou_threshold in [0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95], (
-                f"iou_threshold must be one of [0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95], "
-                f"but got {iou_threshold}"
-            )
-
-    def _convert_to_coco(self):
-        cocoGt_json = sly2coco(
-            self.gt_project_path,
-            is_dt_dataset=False,
-            accepted_shapes=["polygon", "bitmap"],
-            progress=self.pbar,
-            classes_whitelist=self.classes_whitelist,
-        )
-        cocoDt_json = sly2coco(
-            self.dt_project_path,
-            is_dt_dataset=True,
-            accepted_shapes=["polygon", "bitmap"],
-            progress=self.pbar,
-            classes_whitelist=self.classes_whitelist,
-        )
-        if len(cocoGt_json["annotations"]) == 0:
-            raise ValueError("Not found any annotations in GT project")
-        if len(cocoDt_json["annotations"]) == 0:
-            raise ValueError(
-                "Not found any predictions. "
-                "Please make sure that your model produces predictions."
-            )
-        assert (
-            cocoDt_json["categories"] == cocoGt_json["categories"]
-        ), "Object classes in GT and DT projects are different"
-        assert [f'{x["dataset"]}/{x["file_name"]}' for x in cocoDt_json["images"]] == [
-            f'{x["dataset"]}/{x["file_name"]}' for x in cocoGt_json["images"]
-        ], "Images in GT and DT projects are different"
-        return cocoGt_json, cocoDt_json
-
-    def _dump_datasets(self):
-        cocoGt_path, cocoDt_path, eval_data_path = self._get_eval_paths()
-        dump_json_file(self.cocoGt_json, cocoGt_path, indent=None)
-        dump_json_file(self.cocoDt_json, cocoDt_path, indent=None)
-
-    def _dump_eval_results(self):
-        cocoGt_path, cocoDt_path, eval_data_path = self._get_eval_paths()
-        self._dump_pickle(self.eval_data, eval_data_path)
-
-    def _get_eval_paths(self):
-        base_dir = self.result_dir
-        cocoGt_path = os.path.join(base_dir, "cocoGt.json")
-        cocoDt_path = os.path.join(base_dir, "cocoDt.json")
-        eval_data_path = os.path.join(base_dir, "eval_data.pkl")
-        return cocoGt_path, cocoDt_path, eval_data_path

supervisely/nn/benchmark/utils.py

@@ -1,13 +0,0 @@
-from supervisely.nn.inference import SessionJSON
-
-WORKSPACE_NAME = "Model Benchmark: predictions and differences"
-WORKSPACE_DESCRIPTION = "Technical workspace for model benchmarking. Contains predictions and differences between ground truth and predictions."
-
-def try_set_conf_auto(session: SessionJSON, conf: float):
-    conf_names = ["conf", "confidence", "confidence_threshold", "confidence_thresh"]
-    default = session.get_default_inference_settings()
-    for name in conf_names:
-        if name in default:
-            session.inference_settings[name] = conf
-            return True
-    return False

supervisely/nn/benchmark/visualization/inference_speed/__init__.py

@@ -1,19 +0,0 @@
-from supervisely.nn.benchmark.visualization.inference_speed.speedtest_batch import (
-    SpeedtestBatch,
-)
-from supervisely.nn.benchmark.visualization.inference_speed.speedtest_intro import (
-    SpeedtestIntro,
-)
-from supervisely.nn.benchmark.visualization.inference_speed.speedtest_overview import (
-    SpeedtestOverview,
-)
-from supervisely.nn.benchmark.visualization.inference_speed.speedtest_real_time import (
-    SpeedtestRealTime,
-)
-
-SPEEDTEST_METRICS = [
-    SpeedtestIntro,
-    SpeedtestOverview,
-    # SpeedtestRealTime,
-    SpeedtestBatch,
-]

supervisely/nn/benchmark/visualization/inference_speed/speedtest_batch.py

@@ -1,161 +0,0 @@
-from __future__ import annotations
-
-from typing import TYPE_CHECKING
-
-from supervisely.nn.benchmark.visualization.vis_metric_base import MetricVis
-from supervisely.nn.benchmark.visualization.vis_widgets import Schema, Widget
-
-if TYPE_CHECKING:
-    from supervisely.nn.benchmark.visualization.visualizer import Visualizer
-
-
-class SpeedtestBatch(MetricVis):
-
-    def __init__(self, loader: Visualizer) -> None:
-        super().__init__(loader)
-        self.schema = Schema(
-            self._loader.inference_speed_text,
-            markdown_batch_inference=Widget.Markdown(title="Batch inference"),
-            chart=Widget.Chart(),
-        )
-
-    def get_figure(self, widget: Widget.Chart):  #  -> Optional[go.Figure]
-        import plotly.graph_objects as go  # pylint: disable=import-error
-        from plotly.subplots import make_subplots  # pylint: disable=import-error
-
-        fig = make_subplots(cols=2)
-
-        ms_color = "#e377c2"
-        fps_color = "#17becf"
-
-        temp_res = {}
-        for test in self._loader.speedtest["speedtest"]:
-            batch_size = test["batch_size"]
-
-            std = test["benchmark_std"]["total"]
-            ms = test["benchmark"]["total"]
-            fps = round(1000 / test["benchmark"]["total"] * batch_size)
-            # fps_upper = round(1000 / (ms - std) * batch_size)
-            # fps_std = round(fps_upper - fps)
-
-            ms_line = temp_res.setdefault("ms", {})
-            fps_line = temp_res.setdefault("fps", {})
-            ms_std_line = temp_res.setdefault("ms_std", {})
-            # fps_std_line = temp_res.setdefault("fps_std", {})
-
-            ms_line[batch_size] = ms
-            fps_line[batch_size] = fps
-            ms_std_line[batch_size] = round(std, 2)
-            # fps_std_line[batch_size] = fps_std
-
-        fig.add_trace(
-            go.Scatter(
-                x=list(temp_res["ms"].keys()),
-                y=list(temp_res["ms"].values()),
-                name="Infrence time (ms)",
-                line=dict(color=ms_color),
-                customdata=list(temp_res["ms_std"].values()),
-                error_y=dict(
-                    type="data",
-                    array=list(temp_res["ms_std"].values()),
-                    visible=True,
-                    color="rgba(227, 119, 194, 0.7)",
-                ),
-                hovertemplate="Batch Size: %{x}<br>Time: %{y:.2f} ms<br> Standard deviation: %{customdata:.2f} ms<extra></extra>",
-            ),
-            col=1,
-            row=1,
-        )
-        fig.add_trace(
-            go.Scatter(
-                x=list(temp_res["fps"].keys()),
-                y=list(temp_res["fps"].values()),
-                name="FPS",
-                line=dict(color=fps_color),
-                # customdata=list(temp_res["fps_std"].values()),
-                # error_y=dict(
-                #     type="data",
-                #     array=list(temp_res["fps_std"].values()),
-                #     visible=True,
-                #     color="rgba(23, 190, 207, 0.7)",
-                # ),
-                hovertemplate="Batch Size: %{x}<br>FPS: %{y:.2f}<extra></extra>",  # <br> Standard deviation: %{customdata:.2f}<extra></extra>",
-            ),
-            col=2,
-            row=1,
-        )
-
-        fig.update_xaxes(title_text="Batch size", col=1, dtick=1)
-        fig.update_xaxes(title_text="Batch size", col=2, dtick=1)
-
-        fig.update_yaxes(title_text="Time (ms)", col=1)
-        fig.update_yaxes(title_text="FPS", col=2)
-        fig.update_layout(height=400)
-
-        return fig
-
-
-## ========================backup (for public benchmark)==========================
-# class SpeedtestBatch(MetricVis):
-
-#     def __init__(self, loader: Visualizer) -> None:
-#         super().__init__(loader)
-#         self.switchable: bool = True
-#         self.schema = Schema(
-#             self._loader.inference_speed_text,
-#             markdown_batch_inference=Widget.Markdown(title="Batch inference"),
-#             chart1=Widget.Chart(switch_key="ms"),
-#             chart2=Widget.Chart(switch_key="fps"),
-#         )
-
-#     def get_figure(self, widget: Widget.Chart):  #  -> Optional[go.Figure]
-#         import plotly.graph_objects as go  # pylint: disable=import-error
-
-#         colors = iter(["#17becf", "#e377c2", "#bcbd22", "#ff7f0e", "#9467bd", "#2ca02c"])
-
-#         data = {}
-#         for test in self._loader.speedtest["speedtest"]:
-#             device = "GPU" if "cuda" in test["device"] else "CPU"
-#             runtime = test["runtime"]
-#             runtime_and_device = f"{device} {runtime}"
-#             batch_size = test["batch_size"]
-
-#             if widget.switch_key == "ms":
-#                 total = test["benchmark"]["total"]
-#             else:
-#                 total = round(1000 / test["benchmark"]["total"] * batch_size)
-
-#             line = data.setdefault(runtime_and_device, {})
-#             line[batch_size] = total
-
-#         fig = go.Figure()
-#         min_x, max_y, min_x_idx = float("inf"), 0, 0
-#         for idx, (runtime_and_device, line) in enumerate(data.items()):
-#             max_y = max(max_y, max(line.values()))
-#             if min_x > min(line.keys()):
-#                 min_x = min(line.keys())
-#                 min_x_idx = idx
-#             fig.add_trace(
-#                 go.Scatter(
-#                     x=list(line.keys()),
-#                     y=list(line.values()),
-#                     mode="lines+markers",
-#                     name=runtime_and_device,
-#                     line=dict(color=next(colors)),
-#                 )
-#             )
-
-#         fig.update_layout(
-#             xaxis_title="Batch Size",
-#             yaxis_title="Time (ms)" if widget.switch_key == "ms" else "Images per second (FPS)",
-#             legend=dict(x=min_x_idx, y=max_y * 0.7),
-#             width=700,
-#             height=500,
-#         )
-
-#         if widget.switch_key == "ms":
-#             hovertemplate = "Batch Size: %{x}<br>Time: %{y:.2f} ms<extra></extra>"
-#         else:
-#             hovertemplate = "Batch Size: %{x}<br>FPS: %{y:.2f}<extra></extra>"
-#         fig.update_traces(hovertemplate=hovertemplate)
-#         return fig