supervisely 6.73.418__py3-none-any.whl → 6.73.420__py3-none-any.whl

{supervisely-6.73.418.dist-info → supervisely-6.73.420.dist-info}/RECORD

@@ -52,7 +52,7 @@ supervisely/api/video_annotation_tool_api.py,sha256=3A9-U8WJzrTShP_n9T8U01M9FzGY
 supervisely/api/workspace_api.py,sha256=24O9uR5eIA2JdD0eQLi9LGaaHISdb2gUqnxJtx7bTew,9222
 supervisely/api/entity_annotation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/api/entity_annotation/entity_annotation_api.py,sha256=R7irdsYmUecsibuUFbcPRiS6tV3GnCHi9NfWeuoN7_0,3085
-supervisely/api/entity_annotation/figure_api.py,sha256=KjTpHd7Tl--sG56bC16Ih0cZ7h94lAYpyviOmwOKdCU,35759
+supervisely/api/entity_annotation/figure_api.py,sha256=0tG-eJ3HEzcOSQBKSmsAzB-tQ2uZZLyBGsYxA1Bk5us,38052
 supervisely/api/entity_annotation/object_api.py,sha256=gbcNvN_KY6G80Me8fHKQgryc2Co7VU_kfFd1GYILZ4E,8875
 supervisely/api/entity_annotation/tag_api.py,sha256=IapvSZmakjdOn0yvqP2tQRY8gkZg0bcvIZBwWRcafrg,18996
 supervisely/api/nn/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -895,9 +895,9 @@ supervisely/nn/benchmark/visualization/widgets/table/__init__.py,sha256=47DEQpj8
 supervisely/nn/benchmark/visualization/widgets/table/table.py,sha256=atmDnF1Af6qLQBUjLhK18RMDKAYlxnsuVHMSEa5a-e8,4319
 supervisely/nn/inference/__init__.py,sha256=QFukX2ip-U7263aEPCF_UCFwj6EujbMnsgrXp5Bbt8I,1623
 supervisely/nn/inference/cache.py,sha256=rfmb1teJ9lNDfisUSh6bwDCVkPZocn8GMvDgLQktnbo,35023
-supervisely/nn/inference/inference.py,sha256=QTdx7RLekCs5JksRSc2skOlA9buNl05FtB6j9LcgKMQ,199183
+supervisely/nn/inference/inference.py,sha256=tOEoUTvdmFiHsGKri_9pvlu4iqx30tB0aMXr9q8-L3c,199776
 supervisely/nn/inference/inference_request.py,sha256=y6yw0vbaRRcEBS27nq3y0sL6Gmq2qLA_Bm0GrnJGegE,14267
-supervisely/nn/inference/session.py,sha256=dIg2F-OBl68pUzcmtmcI0YQIp1WWNnrJTVMjwFN91Q4,35824
+supervisely/nn/inference/session.py,sha256=XUqJ_CqHk3ZJYkWxdnErN_6afCpIBU76nq6Ek7DiOQI,35792
 supervisely/nn/inference/uploader.py,sha256=21a9coOimCHhEqAbV-llZWcp12847DEMoQp3N16bpK0,5425
 supervisely/nn/inference/video_inference.py,sha256=8Bshjr6rDyLay5Za8IB8Dr6FURMO2R_v7aELasO8pR4,5746
 supervisely/nn/inference/gui/__init__.py,sha256=wCxd-lF5Zhcwsis-wScDA8n1Gk_1O00PKgDviUZ3F1U,221
@@ -905,7 +905,7 @@ supervisely/nn/inference/gui/gui.py,sha256=0OjGcU0KGZgWfLVQkBbljNy-QV22pdZ0bbpPv
 supervisely/nn/inference/gui/serving_gui.py,sha256=JCIVp3B_tX0VKMMBJ-TdRzzAMnAL-sdqHnb1vd28r50,8596
 supervisely/nn/inference/gui/serving_gui_template.py,sha256=V2FJYLyWT9a315npIeVkEEpB8Xc-AOL7TgG0wgM08sc,9777
 supervisely/nn/inference/instance_segmentation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/inference/instance_segmentation/instance_segmentation.py,sha256=TWasw61P4CDiWi2zWuIYJLZ9woLA5IxWtUNRn9u6qEU,2211
+supervisely/nn/inference/instance_segmentation/instance_segmentation.py,sha256=7B5PLkbCv6e5oqqia6Ugf3OUlff_83kYfcAk_3GJXRg,2261
 supervisely/nn/inference/instance_segmentation/dashboard/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/inference/instance_segmentation/dashboard/classes_ui.py,sha256=glu31SzXVxSK2tEgDPNGNCG4_S72XPHY9u1U5lUckSg,2915
 supervisely/nn/inference/instance_segmentation/dashboard/deploy_ui.py,sha256=XbLqrLhZASSbjUM5Kt29IRSdPnv-nVNQUU1U5Xdw7FU,1215
@@ -916,7 +916,7 @@ supervisely/nn/inference/interactive_segmentation/__init__.py,sha256=47DEQpj8HBS
 supervisely/nn/inference/interactive_segmentation/functional.py,sha256=3GaeeOemji_ym0-C2mwj6SVEhnPkq7v3KCc4npw3iZ8,4905
 supervisely/nn/inference/interactive_segmentation/interactive_segmentation.py,sha256=vX1H9eaR8oRfMecQxJfpu6hGxbtf8bEESGJp_fPmfWc,20402
 supervisely/nn/inference/object_detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/inference/object_detection/object_detection.py,sha256=Ki4updsAid1KOI2ahcdVVZ9lzdyRcYKyuQyzSz_9sXQ,1746
+supervisely/nn/inference/object_detection/object_detection.py,sha256=aDM29aMeM3UMHk5c28sB2UK5t1Ir5NMuQwzqH2vxg_Y,1796
 supervisely/nn/inference/object_detection_3d/__init__.py,sha256=1N1fTXgJ6zbTVhM4CXwyobQy5pe1Sb1tNm8vm-i6DaE,94
 supervisely/nn/inference/object_detection_3d/object_detection_3d.py,sha256=GmBz7VQ9-nl6EGrTb0b6Icm-TVdXT0qLiKg1pbvCUws,5601
 supervisely/nn/inference/pose_estimation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -970,36 +970,23 @@ supervisely/nn/legacy/pytorch/weights.py,sha256=Zb9kcpUCg6ykr7seO53CkKSQa2K44wo8
 supervisely/nn/legacy/training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 supervisely/nn/legacy/training/eval_planner.py,sha256=zN9b0_CX7sWGdC8e6riTvD-NOUc3_Xduyhj00S7PEIo,1311
 supervisely/nn/model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/model/model_api.py,sha256=jR1vCVHj70xbuYyYrpcBhUZYdnw8w5DsP_ZcQlo24qE,9945
-supervisely/nn/model/prediction.py,sha256=N3oO9s3NDiC5CFvW8utfU8rz3bfpCl37Sk4VEBH94Bc,11307
-supervisely/nn/model/prediction_session.py,sha256=sy0FSQaWSmT8i0RkR4J8oIn3Ek4IDVJNBR1Tg4mulkM,25523
-supervisely/nn/tracker/__init__.py,sha256=LiojByb5kGsTQ49lWuboEh7B4JUwM1vfz81J8kJlLYo,337
-supervisely/nn/tracker/tracker.py,sha256=Hs0c07l9IVF86jvjloNAGJsSZAHuNQZf0kVaUHfw3Fs,9694
-supervisely/nn/tracker/bot_sort/__init__.py,sha256=zEs5eT8NQMrM5dtSn7kbI2aWpgS2rvO7aNmrAB8v0VU,632
-supervisely/nn/tracker/bot_sort/basetrack.py,sha256=rq7wVutxNhOm_IEezzSiKzonxhZu7B1Are_7g6Jn-oY,1112
-supervisely/nn/tracker/bot_sort/bot_sort.py,sha256=JACqFZaCInA3bOtYUSnFEmLVEl_2YxC5mlkowEVGI2M,17285
-supervisely/nn/tracker/bot_sort/fast_reid_interface.py,sha256=qVV5bltpWUiAXjEGApnxXlwAVSNmO_vENinEhQOdPHE,4819
-supervisely/nn/tracker/bot_sort/matching.py,sha256=n9Ecr06tBmfUemkrOFVQMOeV6ddZW_V9YgKkNF5XAtU,4132
-supervisely/nn/tracker/bot_sort/sly_tracker.py,sha256=XPHUcZ9eQ2KJ7zNM-LF0HAyuPvMGsxgNTyVqYY7oeS8,15003
-supervisely/nn/tracker/deep_sort/__init__.py,sha256=X7qn0rDn3nUuha0F2swPmnplmB6TENARL3nUT65QHiE,156
-supervisely/nn/tracker/deep_sort/deep_sort.py,sha256=dC4XJnxqAiVxTAVCBdDg6fc1NkE__6v8EzqBBTg4zRo,10153
-supervisely/nn/tracker/deep_sort/generate_clip_detections.py,sha256=-NU4qyD2G_ZKl1T7wRqfrG0mzX-7DGZpUXEjKH8nlX8,2959
-supervisely/nn/tracker/deep_sort/preprocessing.py,sha256=YIR8tOot8NpBi8iEdAE2oDlqPHBwSfXLC3BRSN8kUqU,1906
-supervisely/nn/tracker/deep_sort/sly_tracker.py,sha256=uhOiwJMt7kh53X_zeWecSm6f38id8KS9Bh-Ra4sLzro,9881
-supervisely/nn/tracker/deep_sort/deep_sort/__init__.py,sha256=RleTF3kMKdZteclPHRm7E49pw1I1GlooqToAv3YmBd0,27
-supervisely/nn/tracker/deep_sort/deep_sort/detection.py,sha256=cS7YqK8RPbr7C3l6myKTHGBvQbYoKxnEyVa4ZGVbsLY,1430
-supervisely/nn/tracker/deep_sort/deep_sort/iou_matching.py,sha256=HSzn9FjOSHrqH9h6qJlYe1i4o0ZJhjERxCcuIYnLmPE,2830
-supervisely/nn/tracker/deep_sort/deep_sort/kalman_filter.py,sha256=wDSbs2QA3cnnWB-WAzjNcKKqGiNZmfpN0_Cm9dTxU38,7888
-supervisely/nn/tracker/deep_sort/deep_sort/linear_assignment.py,sha256=hAqMNk2CFPDJvmGJCfNbGVngUgKGM2oYldaGaU2zWC4,7871
-supervisely/nn/tracker/deep_sort/deep_sort/nn_matching.py,sha256=U0NYReianEohMc9eA_eAuXjqMkqkNjWlq40S7VvYKHs,5469
-supervisely/nn/tracker/deep_sort/deep_sort/track.py,sha256=eNvBlhhBcTzyTWOX_TKyT3sWJM6fSz3vPi30kfz8wE4,4976
-supervisely/nn/tracker/deep_sort/deep_sort/tracker.py,sha256=cz--uel4ROLHPem8dOofitCoQj_bTd8srWFp2FpaBR0,5357
-supervisely/nn/tracker/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-supervisely/nn/tracker/utils/gmc.py,sha256=3JX8979H3NA-YHNaRQyj9Z-xb9qtyMittPEjGw8y2Jo,11557
-supervisely/nn/tracker/utils/kalman_filter.py,sha256=eSFmCjM0mikHCAFvj-KCVzw-0Jxpoc3Cfc2NWEjJC1Q,17268
-supervisely/nn/tracking/__init__.py,sha256=Ld1ed7ZZQZPkhX-5Xr-UbHZx5zLCm2-tInHnPhioOak,50
-supervisely/nn/tracking/boxmot.py,sha256=H9cQjYGL9nX_TLrfKDChhljTIiE9lffcgbwWCf_4PJU,4277
-supervisely/nn/tracking/tracking.py,sha256=WNrNm02B1pspA3d_AmzSJ-54RZTqWV2NZiC7FHe88bo,857
+supervisely/nn/model/model_api.py,sha256=tSstGGdzm3cHc81P7IoM447sMVesUYJpspzMqUY70pg,10322
+supervisely/nn/model/prediction.py,sha256=C_lbgfDQD29MrBflSQNsxRghwnJ5LmPwMf6S4y2hwoY,11795
+supervisely/nn/model/prediction_session.py,sha256=Lyr3D6KwvjwHtzow6OYdNsoEecdP4ys2RC-usZ9PCM0,26639
+supervisely/nn/tracker/__init__.py,sha256=fTyXg-q_LuYx9sv6TueDDhxCfwQmDxUkIK4iLZgfBOk,283
+supervisely/nn/tracker/base_tracker.py,sha256=2d23JlHizOqVye324YT20EE8RP52uwoQUkPYvPXJTdw,1668
+supervisely/nn/tracker/botsort_tracker.py,sha256=jNtzhdUMoBYMvvreEV4bFQbYav97koiD4gLU5LvICr8,9817
+supervisely/nn/tracker/botsort/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+supervisely/nn/tracker/botsort/botsort_config.yaml,sha256=q_7Gp1-15lGYOLv7JvxVJ69mm6hbCLbUAl_ZBOYNGpw,535
+supervisely/nn/tracker/botsort/osnet_reid/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/tracker/botsort/osnet_reid/osnet.py,sha256=07-svZiVfzEf92Q3f2ffbgXPePAbO61FenaAsaGDj74,16824
+supervisely/nn/tracker/botsort/osnet_reid/osnet_reid_interface.py,sha256=Qzp35-V8xv2zQUIr6vvNrTzyvdxCaa2USJVbyBae6DI,3227
+supervisely/nn/tracker/botsort/tracker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+supervisely/nn/tracker/botsort/tracker/basetrack.py,sha256=oPcXpQWev6YmpjzqWwQKZJrNdyAHL1A8q_ok10nwgvY,1111
+supervisely/nn/tracker/botsort/tracker/gmc.py,sha256=E6LkkVEYeBUjKaQ7VnYxMAj0fdDDWH8Es_tC1a0Z0rs,11754
+supervisely/nn/tracker/botsort/tracker/kalman_filter.py,sha256=waTArMcbmpHAzb57aJ-IcS1o5-i-TX5U-0N_M_28nlo,9671
+supervisely/nn/tracker/botsort/tracker/matching.py,sha256=bgnheHwWD3XZSI3OJVfdrU5bYJ44rxPHzzSElfg6LZM,6600
+supervisely/nn/tracker/botsort/tracker/mc_bot_sort.py,sha256=AE_yi4pVg_bIsK-6-ZlPziqb98tA-9iWgjT8aRE-8sA,17775
 supervisely/nn/training/__init__.py,sha256=gY4PCykJ-42MWKsqb9kl-skemKa8yB6t_fb5kzqR66U,111
 supervisely/nn/training/train_app.py,sha256=c71Y9rV-0qnZ0VsE156HS9Q5Fowg8RoGsItyYFjdyPA,125210
 supervisely/nn/training/gui/__init__.py,sha256=Nqnn8clbgv-5l0PgxcTOldg8mkMKrFn4TvPL-rYUUGg,1
@@ -1042,7 +1029,7 @@ supervisely/project/data_version.py,sha256=P5Lui6i64pYeJWmAdGJDv8GRXxjfpSSZ8zT_M
 supervisely/project/download.py,sha256=yCFpRum_q8fbY_z2mcRAhYAcYFcDc215ldioO3Gzg3Q,28680
 supervisely/project/pointcloud_episode_project.py,sha256=ahwL79Ojf5gLdvAph5SLKXr66jmVWzgiOXLsk2P8eVQ,48433
 supervisely/project/pointcloud_project.py,sha256=NcrsMf673cITLoErJhcdQN85w3k9TBqolEbWR4qjPZQ,56872
-supervisely/project/project.py,sha256=bK_TWDLHmTSoxFEUqzSk-FJzddpb0BqsQfQzzwaZu-Y,240401
+supervisely/project/project.py,sha256=Xl_L_dRJp0KZJMioabXWGO2Zt1X6dl2W9v4-Zt66zYs,246561
 supervisely/project/project_meta.py,sha256=UTQPstRmRJvbtCcQ1noCtzcw3Sd4llwRMHes-Sz-JQg,51429
 supervisely/project/project_settings.py,sha256=NLThzU_DCynOK6hkHhVdFyezwprn9UqlnrLDe_3qhkY,9347
 supervisely/project/project_type.py,sha256=7mQ7zg6r7Bm2oFn5aR8n_PeLqMmOaPZd6ph7Z8ZISTw,608
@@ -1116,9 +1103,9 @@ 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-6.73.418.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-supervisely-6.73.418.dist-info/METADATA,sha256=4Q72_bAv1i77E0O3WymuG3cr5C3mAl1Ab2dw4fdmM-8,35254
-supervisely-6.73.418.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-supervisely-6.73.418.dist-info/entry_points.txt,sha256=U96-5Hxrp2ApRjnCoUiUhWMqijqh8zLR03sEhWtAcms,102
-supervisely-6.73.418.dist-info/top_level.txt,sha256=kcFVwb7SXtfqZifrZaSE3owHExX4gcNYe7Q2uoby084,28
-supervisely-6.73.418.dist-info/RECORD,,
+supervisely-6.73.420.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+supervisely-6.73.420.dist-info/METADATA,sha256=6wWuelPBg3V20xDmnkT_ZYPt4RxkNbbN94i0z9Q2y1M,35338
+supervisely-6.73.420.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+supervisely-6.73.420.dist-info/entry_points.txt,sha256=U96-5Hxrp2ApRjnCoUiUhWMqijqh8zLR03sEhWtAcms,102
+supervisely-6.73.420.dist-info/top_level.txt,sha256=kcFVwb7SXtfqZifrZaSE3owHExX4gcNYe7Q2uoby084,28
+supervisely-6.73.420.dist-info/RECORD,,

supervisely/nn/tracker/bot_sort/__init__.py

@@ -1,21 +0,0 @@
-import torch  # pylint: disable=import-error
-
-try:
-    import fastreid
-except ImportError:
-    import sys
-    from pathlib import Path
-
-    fast_reid_repo_url = "https://github.com/supervisely-ecosystem/fast-reid.git"
-    fast_reid_parent_path = Path(__file__).parent
-    fast_reid_path = fast_reid_parent_path.joinpath("fast_reid")
-    if not fast_reid_path.exists():
-        import subprocess
-
-        subprocess.run(["git", "clone", fast_reid_repo_url, str(fast_reid_path.resolve())])
-
-    sys.path.insert(0, str(fast_reid_path.resolve()))
-
-    import fastreid
-
-from supervisely.nn.tracker.bot_sort.sly_tracker import BoTTracker

supervisely/nn/tracker/bot_sort/fast_reid_interface.py

@@ -1,152 +0,0 @@
-import cv2
-import matplotlib.pyplot as plt
-import numpy as np
-import torch  # pylint: disable=import-error
-import torch.nn.functional as F  # pylint: disable=import-error
-from fastreid.config import get_cfg  # pylint: disable=import-error
-from fastreid.modeling.meta_arch import build_model  # pylint: disable=import-error
-from fastreid.utils.checkpoint import Checkpointer  # pylint: disable=import-error
-
-# from torch.backends import cudnn
-
-
-# cudnn.benchmark = True
-
-
-def setup_cfg(config_file, opts):
-    # load config from file and command-line arguments
-    cfg = get_cfg()
-    cfg.merge_from_file(config_file)
-    cfg.merge_from_list(opts)
-    cfg.MODEL.BACKBONE.PRETRAIN = False
-
-    cfg.freeze()
-
-    return cfg
-
-
-def postprocess(features):
-    # Normalize feature to compute cosine distance
-    features = F.normalize(features)
-    features = features.cpu().data.numpy()
-    return features
-
-
-def preprocess(image, input_size):
-    if len(image.shape) == 3:
-        padded_img = np.ones((input_size[1], input_size[0], 3), dtype=np.uint8) * 114
-    else:
-        padded_img = np.ones(input_size) * 114
-    img = np.array(image)
-    r = min(input_size[1] / img.shape[0], input_size[0] / img.shape[1])
-    resized_img = cv2.resize(
-        img,
-        (int(img.shape[1] * r), int(img.shape[0] * r)),
-        interpolation=cv2.INTER_LINEAR,
-    )
-    padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img
-
-    return padded_img, r
-
-
-class FastReIDInterface:
-    def __init__(self, config_file, weights_path, device, batch_size=8):
-        super(FastReIDInterface, self).__init__()
-        if device != "cpu":
-            self.device = "cuda"
-        else:
-            self.device = "cpu"
-
-        self.batch_size = batch_size
-
-        self.cfg = setup_cfg(config_file, ["MODEL.WEIGHTS", weights_path])
-
-        self.model = build_model(self.cfg)
-        self.model.eval()
-
-        Checkpointer(self.model).load(weights_path)
-
-        if self.device != "cpu":
-            self.model = self.model.eval().to(device="cuda").half()
-        else:
-            self.model = self.model.eval()
-
-        self.pH, self.pW = self.cfg.INPUT.SIZE_TEST
-
-    def inference(self, image, detections):
-
-        if detections is None or np.size(detections) == 0:
-            return []
-
-        H, W, _ = np.shape(image)
-
-        batch_patches = []
-        patches = []
-        for d in range(np.size(detections, 0)):
-            tlbr = detections[d, :4].astype(np.int_)
-            tlbr[0] = max(0, tlbr[0])
-            tlbr[1] = max(0, tlbr[1])
-            tlbr[2] = min(W - 1, tlbr[2])
-            tlbr[3] = min(H - 1, tlbr[3])
-            patch = image[tlbr[1] : tlbr[3], tlbr[0] : tlbr[2], :]
-
-            # the model expects RGB inputs
-            patch = patch[:, :, ::-1]
-
-            # Apply pre-processing to image.
-            patch = cv2.resize(
-                patch, tuple(self.cfg.INPUT.SIZE_TEST[::-1]), interpolation=cv2.INTER_LINEAR
-            )
-            # patch, scale = preprocess(patch, self.cfg.INPUT.SIZE_TEST[::-1])
-
-            # plt.figure()
-            # plt.imshow(patch)
-            # plt.show()
-
-            # Make shape with a new batch dimension which is adapted for network input
-            patch = torch.as_tensor(patch.astype("float32").transpose(2, 0, 1))
-            patch = patch.to(device=self.device).half()
-
-            patches.append(patch)
-
-            if (d + 1) % self.batch_size == 0:
-                patches = torch.stack(patches, dim=0)
-                batch_patches.append(patches)
-                patches = []
-
-        if len(patches):
-            patches = torch.stack(patches, dim=0)
-            batch_patches.append(patches)
-
-        features = np.zeros((0, 2048))
-        # features = np.zeros((0, 768))
-
-        for patches in batch_patches:
-
-            # Run model
-            patches_ = torch.clone(patches)
-            pred = self.model(patches)
-            pred[torch.isinf(pred)] = 1.0
-
-            feat = postprocess(pred)
-
-            nans = np.isnan(np.sum(feat, axis=1))
-            if np.isnan(feat).any():
-                for n in range(np.size(nans)):
-                    if nans[n]:
-                        # patch_np = patches[n, ...].squeeze().transpose(1, 2, 0).cpu().numpy()
-                        patch_np = patches_[n, ...]
-                        patch_np_ = torch.unsqueeze(patch_np, 0)
-                        pred_ = self.model(patch_np_)
-
-                        patch_np = torch.squeeze(patch_np).cpu()
-                        patch_np = torch.permute(patch_np, (1, 2, 0)).int()
-                        patch_np = patch_np.numpy()
-
-                        plt.figure()
-                        plt.imshow(patch_np)
-                        plt.show()
-
-            features = np.vstack((features, feat))
-
-        return features

supervisely/nn/tracker/bot_sort/matching.py

@@ -1,127 +0,0 @@
-import lap  # pylint: disable=import-error
-import numpy as np
-from cython_bbox import bbox_overlaps as bbox_ious  # pylint: disable=import-error
-from scipy.spatial.distance import cdist
-
-from supervisely.nn.tracker.utils import kalman_filter
-
-
-def linear_assignment(cost_matrix, thresh):
-    if cost_matrix.size == 0:
-        return (
-            np.empty((0, 2), dtype=int),
-            tuple(range(cost_matrix.shape[0])),
-            tuple(range(cost_matrix.shape[1])),
-        )
-    matches, unmatched_a, unmatched_b = [], [], []
-    cost, x, y = lap.lapjv(cost_matrix, extend_cost=True, cost_limit=thresh)
-    for ix, mx in enumerate(x):
-        if mx >= 0:
-            matches.append([ix, mx])
-    unmatched_a = np.where(x < 0)[0]
-    unmatched_b = np.where(y < 0)[0]
-    matches = np.asarray(matches)
-    return matches, unmatched_a, unmatched_b
-
-
-def ious(atlbrs, btlbrs):
-    """
-    Compute cost based on IoU
-    :type atlbrs: list[tlbr] | np.ndarray
-    :type atlbrs: list[tlbr] | np.ndarray
-
-    :rtype ious np.ndarray
-    """
-    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=float)
-    if ious.size == 0:
-        return ious
-
-    ious = bbox_ious(
-        np.ascontiguousarray(atlbrs, dtype=float), np.ascontiguousarray(btlbrs, dtype=float)
-    )
-
-    return ious
-
-
-def iou_distance(atracks, btracks):
-    """
-    Compute cost based on IoU
-    :type atracks: list[STrack]
-    :type btracks: list[STrack]
-
-    :rtype cost_matrix np.ndarray
-    """
-
-    if (len(atracks) > 0 and isinstance(atracks[0], np.ndarray)) or (
-        len(btracks) > 0 and isinstance(btracks[0], np.ndarray)
-    ):
-        atlbrs = atracks
-        btlbrs = btracks
-    else:
-        atlbrs = [track.tlbr for track in atracks]
-        btlbrs = [track.tlbr for track in btracks]
-    _ious = ious(atlbrs, btlbrs)
-    cost_matrix = 1 - _ious
-
-    return cost_matrix
-
-
-def embedding_distance(tracks, detections, metric="cosine"):
-    """
-    :param tracks: list[STrack]
-    :param detections: list[BaseTrack]
-    :param metric:
-    :return: cost_matrix np.ndarray
-    """
-
-    cost_matrix = np.zeros((len(tracks), len(detections)), dtype=float)
-    if cost_matrix.size == 0:
-        return cost_matrix
-    det_features = np.asarray([track.curr_feat for track in detections], dtype=float)
-    track_features = np.asarray([track.smooth_feat for track in tracks], dtype=float)
-
-    cost_matrix = np.maximum(
-        0.0, cdist(track_features, det_features, metric)
-    )  # / 2.0  # Nomalized features
-    return cost_matrix
-
-
-def fuse_motion(kf, cost_matrix, tracks, detections, only_position=False, lambda_=0.98):
-    if cost_matrix.size == 0:
-        return cost_matrix
-    gating_dim = 2 if only_position else 4
-    gating_threshold = kalman_filter.chi2inv95[gating_dim]
-    # measurements = np.asarray([det.to_xyah() for det in detections])
-    measurements = np.asarray([det.to_xywh() for det in detections])
-    for row, track in enumerate(tracks):
-        gating_distance = kf.gating_distance(
-            track.mean, track.covariance, measurements, only_position, metric="maha"
-        )
-        cost_matrix[row, gating_distance > gating_threshold] = np.inf
-        cost_matrix[row] = lambda_ * cost_matrix[row] + (1 - lambda_) * gating_distance
-    return cost_matrix
-
-
-def fuse_iou(cost_matrix, tracks, detections):
-    if cost_matrix.size == 0:
-        return cost_matrix
-    reid_sim = 1 - cost_matrix
-    iou_dist = iou_distance(tracks, detections)
-    iou_sim = 1 - iou_dist
-    fuse_sim = reid_sim * (1 + iou_sim) / 2
-    det_scores = np.array([det.score for det in detections])
-    det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0)
-    # fuse_sim = fuse_sim * (1 + det_scores) / 2
-    fuse_cost = 1 - fuse_sim
-    return fuse_cost
-
-
-def fuse_score(cost_matrix, detections):
-    if cost_matrix.size == 0:
-        return cost_matrix
-    iou_sim = 1 - cost_matrix
-    det_scores = np.array([det.score for det in detections])
-    det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0)
-    fuse_sim = iou_sim * det_scores
-    fuse_cost = 1 - fuse_sim
-    return fuse_cost