dgenerate-ultralytics-headless 8.3.159__py3-none-any.whl → 8.3.160__py3-none-any.whl

{dgenerate_ultralytics_headless-8.3.159.dist-info → dgenerate_ultralytics_headless-8.3.160.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.159
+Version: 8.3.160
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{dgenerate_ultralytics_headless-8.3.159.dist-info → dgenerate_ultralytics_headless-8.3.160.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dgenerate_ultralytics_headless-8.3.159.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+dgenerate_ultralytics_headless-8.3.160.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
 tests/__init__.py,sha256=b4KP5_q-2IO8Br8YHOSLYnn7IwZS81l_vfEF2YPa2lM,894
 tests/conftest.py,sha256=JjgKSs36ZaGmmtqGmAapmFSoFF1YwyV3IZsOgqt2IVM,2593
 tests/test_cli.py,sha256=Kpfxq_RlbKK1Z8xNScDUbre6GB7neZhXZAYGI1tiDS8,5660
@@ -8,10 +8,10 @@ tests/test_exports.py,sha256=HmMKOTCia9ZDC0VYc_EPmvBTM5LM5eeI1NF_pKjLpd8,9677
 tests/test_integrations.py,sha256=kl_AKmE_Qs1GB0_91iVwbzNxofm_hFTt0zzU6JF-pg4,6323
 tests/test_python.py,sha256=nOoaPDg-0j7ZPRz9-uGFny3uocxjUM1ze5wA3BpGxKQ,27865
 tests/test_solutions.py,sha256=tuf6n_fsI8KvSdJrnc-cqP2qYdiYqCWuVrx0z9dOz3Q,13213
-ultralytics/__init__.py,sha256=sbeS4zCdUAcxO1GIm2GxM1Pk92RQ2Kom9Fk52c9syUs,730
+ultralytics/__init__.py,sha256=dkOuwhLnRXwuh6b1GNUdg_IfIptuMf47ZGNgy9FdV-Y,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
-ultralytics/cfg/__init__.py,sha256=ds63URbbeRj5UxkCSyl62OrNw6HQy7xeit5-0wGDEKg,39699
+ultralytics/cfg/__init__.py,sha256=VIpPHImhjb0XLJquGZrG_LBGZchtOtBSXR7HYTYV2GU,39602
 ultralytics/cfg/default.yaml,sha256=oFG6llJO-Py5H-cR9qs-7FieJamroDLwpbrkhmfROOM,8307
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=_xlEDIJ9XkUo0v_iNL7FW079BoSeZtKSuLteKTtGbA8,3275
 ultralytics/cfg/datasets/DOTAv1.5.yaml,sha256=SHND_CFkojxw5iQD5Mcgju2kCZIl0gW2ajuzv1cqoL0,1224
@@ -106,7 +106,7 @@ ultralytics/cfg/trackers/botsort.yaml,sha256=TpRaK5kH_-QbjCQ7ekM4s_7j8I8ti3q8Hs7
 ultralytics/cfg/trackers/bytetrack.yaml,sha256=6u-tiZlk16EqEwkNXaMrza6PAQmWj_ypgv26LGCtPDg,886
 ultralytics/data/__init__.py,sha256=nAXaL1puCc7z_NjzQNlJnhbVhT9Fla2u7Dsqo7q1dAc,644
 ultralytics/data/annotator.py,sha256=uAgd7K-yudxiwdNqHz0ubfFg5JsfNlae4cgxdvCMyuY,3030
-ultralytics/data/augment.py,sha256=Zxqp6dWKALAbUYha-R_MVrcysdlBj9glm4Nsth_JLrg,129030
+ultralytics/data/augment.py,sha256=jyEXZ1TqJFIdz_oqecsDa4gKDCMC71RGiMJh3kQV9G0,129378
 ultralytics/data/base.py,sha256=mRcuehK1thNuuzQGL6D1AaZkod71oHRdYTod_zdQZQg,19688
 ultralytics/data/build.py,sha256=13gPxCJIZRjgcNh7zbzanCgtyK6_oZM0ho9KQhHcM6c,11153
 ultralytics/data/converter.py,sha256=oKW8ODtvFOKBx9Un8n87xUUm3b5GStU4ViIBH5UDylM,27200
@@ -120,10 +120,10 @@ ultralytics/data/scripts/get_coco.sh,sha256=UuJpJeo3qQpTHVINeOpmP0NYmg8PhEFE3A8J
 ultralytics/data/scripts/get_coco128.sh,sha256=qmRQl_hOKrsdHrTrnyQuFIH01oDz3lfaz138OgGfLt8,650
 ultralytics/data/scripts/get_imagenet.sh,sha256=hr42H16bM47iT27rgS7MpEo-GeOZAYUQXgr0B2cwn48,1705
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=n9mRjOWdX-3T9SroICwdMaRRVi9h98coAfCzDYopyW4,73070
-ultralytics/engine/model.py,sha256=DwugtVxUbCGzpY2pStFMcEloim0ai6LrT6kTbwskSJ8,53302
+ultralytics/engine/exporter.py,sha256=MUgH9gEzeVjnhoZzHuZn958I6c9axE4PTIjJG9uBXuQ,73081
+ultralytics/engine/model.py,sha256=FmLwiKuItVNgoyXhAvesUnD3UeHBzCVzGHDrqB8J4ms,53453
 ultralytics/engine/predictor.py,sha256=88zrgZP91ehwdeGl8BM_cQ_caeuwKIPDy3OzxcRBjTU,22474
-ultralytics/engine/results.py,sha256=Mb8pBTOrBtQh0PQtGVbhRZ_C1VyqYFumjLggiKCRIJs,72295
+ultralytics/engine/results.py,sha256=CHTLuyzGdRyAZJDNajEjF_uOtrWrUUu3zqKdZVA-76M,71989
 ultralytics/engine/trainer.py,sha256=28FeqASvQRxCaK96SXDM-BfPJjqy5KNiWhf8v6GXTug,39785
 ultralytics/engine/tuner.py,sha256=4ue7JbMFQp7JcWhhwCAY-b-xZsjm5VKVlPFDUTyxt_8,12789
 ultralytics/engine/validator.py,sha256=qftJUomb4A-6rSThtST3TccEbc_zTmzovCBBCSpYm3k,16671
@@ -165,7 +165,7 @@ ultralytics/models/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXp
 ultralytics/models/utils/loss.py,sha256=E-61TfLPc04IdeL6IlFDityDoPju-ov0ouWV_cNY4Kg,21254
 ultralytics/models/utils/ops.py,sha256=Pr77n8XW25SUEx4X3bBvXcVIbRdJPoaXJuG0KWWawRQ,15253
 ultralytics/models/yolo/__init__.py,sha256=or0j5xvcM0usMlsFTYhNAOcQUri7reD0cD9JR5b7zDk,307
-ultralytics/models/yolo/model.py,sha256=C0wInQC6rFuFOGpdAen1s2e5LIFDmqevto8uPbpmB8c,18449
+ultralytics/models/yolo/model.py,sha256=xK-Te6D0PGY3vpWQg-HT3TwP0bzPs0XfUjd_L_tVXRs,18752
 ultralytics/models/yolo/classify/__init__.py,sha256=9--HVaNOfI1K7rn_rRqclL8FUAnpfeBrRqEQIaQw2xM,383
 ultralytics/models/yolo/classify/predict.py,sha256=FqAC2YXe25bRwedMZhF3Lw0waoY-a60xMKELhxApP9I,4149
 ultralytics/models/yolo/classify/train.py,sha256=V-hevc6X7xemnpyru84OfTRA77eNnkVSMEz16_OUvo4,10244
@@ -187,11 +187,11 @@ ultralytics/models/yolo/segment/predict.py,sha256=qlprQCZn4_bpjpI08U0MU9Q9_1gpHr
 ultralytics/models/yolo/segment/train.py,sha256=XrPkXUiNu1Jvhn8iDew_RaLLjZA3un65rK-QH9mtNIw,3802
 ultralytics/models/yolo/segment/val.py,sha256=AnvY0O7HhD5xZ2BE2artLTAVW4SNmHbVopBJsYRcmk8,12328
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
-ultralytics/models/yolo/world/train.py,sha256=94_hgCluzsv39JkBVDmR2gjuycYjeJC8wVrCfrjpENk,7806
+ultralytics/models/yolo/world/train.py,sha256=karlbEdkfAh08ZzYj9nXOiqLsRq5grsbV-XDv3yl6GQ,7819
 ultralytics/models/yolo/world/train_world.py,sha256=YJm37ZTgr0CoE_sYrjxN45w9mICr2RMWfWZrriiHqbM,9022
 ultralytics/models/yolo/yoloe/__init__.py,sha256=6SLytdJtwu37qewf7CobG7C7Wl1m-xtNdvCXEasfPDE,760
 ultralytics/models/yolo/yoloe/predict.py,sha256=TAcT6fiWbV-jOewu9hx_shGI10VLF_6oSPf7jfatBWo,7041
-ultralytics/models/yolo/yoloe/train.py,sha256=Dt6orqXcQTzyoAqMVvleP1FQbXChMvEj3QtxIctr3A0,14047
+ultralytics/models/yolo/yoloe/train.py,sha256=H1Z5yzcYklyfIkT0xR35qq3f7CxmeG2jUhWhbVyE6RA,14060
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=aCV7M8oQOvODFnU4piZdJh3tIrBJYAzZfRVRx1vRgxo,4956
 ultralytics/models/yolo/yoloe/val.py,sha256=yebPkxwKKt__cY05Zbh1YXg4_BKzzpcDc3Cv3FJ5SAA,9769
 ultralytics/nn/__init__.py,sha256=rjociYD9lo_K-d-1s6TbdWklPLjTcEHk7OIlRDJstIE,615
@@ -210,17 +210,17 @@ ultralytics/solutions/ai_gym.py,sha256=wwfTqX7G3mZXneMwiibEfYbVYaJF_JUX3SQdsdQUv
 ultralytics/solutions/analytics.py,sha256=aHwKjSEW_3y47LrzugJbPB3VQGTDQCIb5goiPuxnmrc,12802
 ultralytics/solutions/config.py,sha256=CevL8lzeSbiSAAA514CTiduCg2_Wh04P0RaB_kmwJa8,5404
 ultralytics/solutions/distance_calculation.py,sha256=r05_ufxb2Mpw3EIX8X32PIWlh9rYMADypGhVIPoZYV4,5939
-ultralytics/solutions/heatmap.py,sha256=vEdzLSYCNIFC9CsBWYSnCLiM8xNuYLJ-1i7enjQgOQw,5516
+ultralytics/solutions/heatmap.py,sha256=hBJR_Z3Lu9JcvCaEwnd-uN_WEiXK14FDRXedgaI8oqU,5515
 ultralytics/solutions/instance_segmentation.py,sha256=qsIQkvuR1Ur2bdEsCCJP2IEO1Hz2l0wfR2KUBo247xE,3795
 ultralytics/solutions/object_blurrer.py,sha256=wHbfrudh6li_JADc-dTHGGMI8GU-MvesoTvVlX6YuYc,3998
-ultralytics/solutions/object_counter.py,sha256=djg6XIgOuseoKCEY5PrLRf4Z1JjbTEBXrERRV8dOSlU,9442
+ultralytics/solutions/object_counter.py,sha256=ccKuchrVkNE8AD4EvArtl6LCVf442jTOyc6_7tGua5o,9433
 ultralytics/solutions/object_cropper.py,sha256=mS3iT_CgqfqG9ldM_AM5ptq5bfYFyTycPQY5DxxMlSA,3525
 ultralytics/solutions/parking_management.py,sha256=IfPUn15aelxz6YZNo9WYkVEl5IOVSw8VD0OrpKtExPE,13613
 ultralytics/solutions/queue_management.py,sha256=u0VFzRqa0OxIWY7xXItsXEm073CzkQGFhhXG-6VK3SI,4393
 ultralytics/solutions/region_counter.py,sha256=j6f5VAaE1JWGdWOecZpWMFp6yF1GdCnHjftN6CRybjQ,5967
 ultralytics/solutions/security_alarm.py,sha256=U6FTbg3cthKLfWeLunsFhOJvB6GGmwYDDxZ3K0GCx-Q,6351
 ultralytics/solutions/similarity_search.py,sha256=ri8bf65tt6xyS6Xa-ikj2AgvfCsFOtaQk6IM_k7FhKg,9579
-ultralytics/solutions/solutions.py,sha256=N5t1DgZpuFBbDvLVZ7wRkafmgu8SS1VC9VNjuupglwQ,37532
+ultralytics/solutions/solutions.py,sha256=w9enbzZ02H9M00cGb7SqYsar6hKZfBU52ez-5G8cXJI,37554
 ultralytics/solutions/speed_estimation.py,sha256=chg_tBuKFw3EnFiv_obNDaUXLAo-FypxC7gsDeB_VUI,5878
 ultralytics/solutions/streamlit_inference.py,sha256=SqL-YxU3RCxCKscH2AYUTkmJknilV9jCCco6ufqsFk4,10501
 ultralytics/solutions/trackzone.py,sha256=kIS94rNfL3yVPAtSbnW8F-aLMxXowQtsfKNB-jLezz8,3941
@@ -235,7 +235,7 @@ ultralytics/trackers/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6D
 ultralytics/trackers/utils/gmc.py,sha256=9IvCf5MhBYY9ppVHykN02_oBWHmE98R8EaYFKaykdV0,14032
 ultralytics/trackers/utils/kalman_filter.py,sha256=PPmM0lwBMdT_hGojvfLoUsBUFMBBMNRAxKbMcQa3wJ0,21619
 ultralytics/trackers/utils/matching.py,sha256=uSYtywqi1lE_uNN1FwuBFPyISfDQXHMu8K5KH69nrRI,7160
-ultralytics/utils/__init__.py,sha256=GYsojWuYvvSCKhUtQhzv-HmLjfUJrqZXqvu8bw7HbeU,59523
+ultralytics/utils/__init__.py,sha256=oJZ1o2L2R-EHepFbe_9bAzyiLi3Rd3Cv6gJmgO5jNfc,59437
 ultralytics/utils/autobatch.py,sha256=33m8YgggLIhltDqMXZ5OE-FGs2QiHrl2-LfgY1mI4cw,5119
 ultralytics/utils/autodevice.py,sha256=AvgXFt8c1Cg4icKh0Hbhhz8UmVQ2Wjyfdfkeb2C8zck,8855
 ultralytics/utils/benchmarks.py,sha256=GlsR6SvD3qlus2hVj7SqSNErsejBlIxO0Y7hMc_cWHw,31041
@@ -245,9 +245,9 @@ ultralytics/utils/downloads.py,sha256=YB6rJkcRGQfklUjZqi9dOkTiZaDSqbkGyZEFcZLQkg
 ultralytics/utils/errors.py,sha256=XT9Ru7ivoBgofK6PlnyigGoa7Fmf5nEhyHtnD-8TRXI,1584
 ultralytics/utils/export.py,sha256=0gG_GZNRqHcORJbjQq_1MXEHc3UEfzPAdpOl2X5VoDc,10008
 ultralytics/utils/files.py,sha256=ZCbLGleiF0f-PqYfaxMFAWop88w7U1hpreHXl8b2ko0,8238
-ultralytics/utils/instance.py,sha256=vhqaZRGT_4K9Q3oQH5KNNK4ISOzxlf1_JjauwhuFhu0,18408
+ultralytics/utils/instance.py,sha256=s97d-GXSSCluu-My2DFLAubdk_hf44BuVQ6OCROBrMc,18550
 ultralytics/utils/loss.py,sha256=fbOWc3Iu0QOJiWbi-mXWA9-1otTYlehtmUsI7os7ydM,39799
-ultralytics/utils/metrics.py,sha256=1XaTT3n3tfLms6LOCiEzg_QGHQJzjZmfjFoAYsCCc24,62646
+ultralytics/utils/metrics.py,sha256=fSDA0YV3Bb3ALhmWv0Uy1s8acDwFUymd8Tj1MFNPYyU,62251
 ultralytics/utils/ops.py,sha256=Jkh80ujyi0XDQwNqCUYyomH8NQ145AH9doMUS8Vt8GE,34545
 ultralytics/utils/patches.py,sha256=P2uQy7S4RzSHBfwJEXJsjyuRUluaaUusiVU84lV3moQ,6577
 ultralytics/utils/plotting.py,sha256=SCpG5DHZUPlFUsu72kNH3DYGpsjgkd3eIZ9-QTllY88,47171
@@ -266,8 +266,8 @@ ultralytics/utils/callbacks/neptune.py,sha256=j8pecmlcsM8FGzLKWoBw5xUsi5t8E5HuxY
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
 ultralytics/utils/callbacks/tensorboard.py,sha256=MDPBW7aDes-66OE6YqKXXvqA_EocjzEMHWGM-8z9vUQ,5281
 ultralytics/utils/callbacks/wb.py,sha256=Tm_-aRr2CN32MJkY9tylpMBJkb007-MSRNSQ7rDJ5QU,7521
-dgenerate_ultralytics_headless-8.3.159.dist-info/METADATA,sha256=TuUw0G5ABLwDMNuiQ_NCh9Z4jOMqAKj7zEaH3G5Qx5o,38318
-dgenerate_ultralytics_headless-8.3.159.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dgenerate_ultralytics_headless-8.3.159.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-dgenerate_ultralytics_headless-8.3.159.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-dgenerate_ultralytics_headless-8.3.159.dist-info/RECORD,,
+dgenerate_ultralytics_headless-8.3.160.dist-info/METADATA,sha256=UW5E8ePDgtefP25esNBr8NKHlkgTExMW8TWO4D6oFBY,38318
+dgenerate_ultralytics_headless-8.3.160.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dgenerate_ultralytics_headless-8.3.160.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+dgenerate_ultralytics_headless-8.3.160.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+dgenerate_ultralytics_headless-8.3.160.dist-info/RECORD,,

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.159"
+__version__ = "8.3.160"
 
 import os
 

ultralytics/cfg/__init__.py

@@ -954,8 +954,6 @@ def entrypoint(debug: str = "") -> None:
         from ultralytics import YOLO
 
         model = YOLO(model, task=task)
-    if isinstance(overrides.get("pretrained"), str):
-        model.load(overrides["pretrained"])
 
     # Task Update
     if task != model.task:

ultralytics/data/augment.py

@@ -251,8 +251,7 @@ class Compose:
             >>> multiple_transforms = compose[0:2]  # Returns a Compose object with RandomFlip and RandomPerspective
         """
         assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
-        index = [index] if isinstance(index, int) else index
-        return Compose([self.transforms[i] for i in index])
+        return Compose([self.transforms[i] for i in index]) if isinstance(index, list) else self.transforms[index]
 
     def __setitem__(self, index: Union[list, int], value: Union[list, int]) -> None:
         """
@@ -1560,14 +1559,15 @@ class RandomFlip:
         h = 1 if instances.normalized else h
         w = 1 if instances.normalized else w
 
-        # Flip up-down
+        # WARNING: two separate if and calls to random.random() intentional for reproducibility with older versions
         if self.direction == "vertical" and random.random() < self.p:
             img = np.flipud(img)
             instances.flipud(h)
+            if self.flip_idx is not None and instances.keypoints is not None:
+                instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
         if self.direction == "horizontal" and random.random() < self.p:
             img = np.fliplr(img)
             instances.fliplr(w)
-            # For keypoints
             if self.flip_idx is not None and instances.keypoints is not None:
                 instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
         labels["img"] = np.ascontiguousarray(img)
@@ -2533,9 +2533,9 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
     flip_idx = dataset.data.get("flip_idx", [])  # for keypoints augmentation
     if dataset.use_keypoints:
         kpt_shape = dataset.data.get("kpt_shape", None)
-        if len(flip_idx) == 0 and hyp.fliplr > 0.0:
-            hyp.fliplr = 0.0
-            LOGGER.warning("No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'")
+        if len(flip_idx) == 0 and (hyp.fliplr > 0.0 or hyp.flipud > 0.0):
+            hyp.fliplr = hyp.flipud = 0.0  # both fliplr and flipud require flip_idx
+            LOGGER.warning("No 'flip_idx' array defined in data.yaml, disabling 'fliplr' and 'flipud' augmentations.")
         elif flip_idx and (len(flip_idx) != kpt_shape[0]):
             raise ValueError(f"data.yaml flip_idx={flip_idx} length must be equal to kpt_shape[0]={kpt_shape[0]}")
 
@@ -2546,7 +2546,7 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
             CutMix(dataset, pre_transform=pre_transform, p=hyp.cutmix),
             Albumentations(p=1.0),
             RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
-            RandomFlip(direction="vertical", p=hyp.flipud),
+            RandomFlip(direction="vertical", p=hyp.flipud, flip_idx=flip_idx),
             RandomFlip(direction="horizontal", p=hyp.fliplr, flip_idx=flip_idx),
         ]
     )  # transforms

ultralytics/engine/exporter.py

@@ -1495,7 +1495,7 @@ class NMSModel(torch.nn.Module):
         scores, classes = scores.max(dim=-1)
         self.args.max_det = min(pred.shape[1], self.args.max_det)  # in case num_anchors < max_det
         # (N, max_det, 4 coords + 1 class score + 1 class label + extra_shape).
-        out = torch.zeros(bs, self.args.max_det, boxes.shape[-1] + 2 + extra_shape, **kwargs)
+        out = torch.zeros(pred.shape[0], self.args.max_det, boxes.shape[-1] + 2 + extra_shape, **kwargs)
         for i in range(bs):
             box, cls, score, extra = boxes[i], classes[i], scores[i], extras[i]
             mask = score > self.args.conf

ultralytics/engine/model.py

@@ -777,6 +777,8 @@ class Model(torch.nn.Module):
 
         checks.check_pip_update_available()
 
+        if isinstance(kwargs.get("pretrained", None), (str, Path)):
+            self.load(kwargs["pretrained"])  # load pretrained weights if provided
         overrides = YAML.load(checks.check_yaml(kwargs["cfg"])) if kwargs.get("cfg") else self.overrides
         custom = {
             # NOTE: handle the case when 'cfg' includes 'data'.

ultralytics/engine/results.py

@@ -16,7 +16,6 @@ import torch
 from ultralytics.data.augment import LetterBox
 from ultralytics.utils import LOGGER, DataExportMixin, SimpleClass, ops
 from ultralytics.utils.plotting import Annotator, colors, save_one_box
-from ultralytics.utils.torch_utils import smart_inference_mode
 
 
 class BaseTensor(SimpleClass):
@@ -1204,7 +1203,6 @@ class Keypoints(BaseTensor):
         >>> keypoints_cpu = keypoints.cpu()  # Move keypoints to CPU
     """
 
-    @smart_inference_mode()  # avoid keypoints < conf in-place error
     def __init__(self, keypoints: Union[torch.Tensor, np.ndarray], orig_shape: Tuple[int, int]) -> None:
         """
         Initialize the Keypoints object with detection keypoints and original image dimensions.
@@ -1225,9 +1223,6 @@ class Keypoints(BaseTensor):
         """
         if keypoints.ndim == 2:
             keypoints = keypoints[None, :]
-        if keypoints.shape[2] == 3:  # x, y, conf
-            mask = keypoints[..., 2] < 0.5  # points with conf < 0.5 (not visible)
-            keypoints[..., :2][mask] = 0
         super().__init__(keypoints, orig_shape)
         self.has_visible = self.data.shape[-1] == 3
 

ultralytics/models/yolo/model.py

@@ -406,18 +406,18 @@ class YOLOE(Model):
                 f"Expected equal number of bounding boxes and classes, but got {len(visual_prompts['bboxes'])} and "
                 f"{len(visual_prompts['cls'])} respectively"
             )
-        self.predictor = (predictor or self._smart_load("predictor"))(
-            overrides={
-                "task": self.model.task,
-                "mode": "predict",
-                "save": False,
-                "verbose": refer_image is None,
-                "batch": 1,
-            },
-            _callbacks=self.callbacks,
-        )
+            if not isinstance(self.predictor, yolo.yoloe.YOLOEVPDetectPredictor):
+                self.predictor = (predictor or yolo.yoloe.YOLOEVPDetectPredictor)(
+                    overrides={
+                        "task": self.model.task,
+                        "mode": "predict",
+                        "save": False,
+                        "verbose": refer_image is None,
+                        "batch": 1,
+                    },
+                    _callbacks=self.callbacks,
+                )
 
-        if len(visual_prompts):
             num_cls = (
                 max(len(set(c)) for c in visual_prompts["cls"])
                 if isinstance(source, list) and refer_image is None  # means multiple images
@@ -426,18 +426,19 @@ class YOLOE(Model):
             self.model.model[-1].nc = num_cls
             self.model.names = [f"object{i}" for i in range(num_cls)]
             self.predictor.set_prompts(visual_prompts.copy())
-
-        self.predictor.setup_model(model=self.model)
-
-        if refer_image is None and source is not None:
-            dataset = load_inference_source(source)
-            if dataset.mode in {"video", "stream"}:
-                # NOTE: set the first frame as refer image for videos/streams inference
-                refer_image = next(iter(dataset))[1][0]
-        if refer_image is not None and len(visual_prompts):
-            vpe = self.predictor.get_vpe(refer_image)
-            self.model.set_classes(self.model.names, vpe)
-            self.task = "segment" if isinstance(self.predictor, yolo.segment.SegmentationPredictor) else "detect"
-            self.predictor = None  # reset predictor
+            self.predictor.setup_model(model=self.model)
+
+            if refer_image is None and source is not None:
+                dataset = load_inference_source(source)
+                if dataset.mode in {"video", "stream"}:
+                    # NOTE: set the first frame as refer image for videos/streams inference
+                    refer_image = next(iter(dataset))[1][0]
+            if refer_image is not None:
+                vpe = self.predictor.get_vpe(refer_image)
+                self.model.set_classes(self.model.names, vpe)
+                self.task = "segment" if isinstance(self.predictor, yolo.segment.SegmentationPredictor) else "detect"
+                self.predictor = None  # reset predictor
+        elif isinstance(self.predictor, yolo.yoloe.YOLOEVPDetectPredictor):
+            self.predictor = None  # reset predictor if no visual prompts
 
         return super().predict(source, stream, **kwargs)

ultralytics/models/yolo/world/train.py

@@ -158,7 +158,7 @@ class WorldTrainer(DetectionTrainer):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")
         assert self.model is not None
-        txt_feats = self.model.get_text_pe(texts, batch, cache_clip_model=False)
+        txt_feats = de_parallel(self.model).get_text_pe(texts, batch, cache_clip_model=False)
         txt_map = dict(zip(texts, txt_feats.squeeze(0)))
         torch.save(txt_map, cache_path)
         return txt_map

ultralytics/models/yolo/yoloe/train.py

@@ -222,7 +222,7 @@ class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")
         assert self.model is not None
-        txt_feats = self.model.get_text_pe(texts, batch, without_reprta=True, cache_clip_model=False)
+        txt_feats = de_parallel(self.model).get_text_pe(texts, batch, without_reprta=True, cache_clip_model=False)
         txt_map = dict(zip(texts, txt_feats.squeeze(0)))
         torch.save(txt_map, cache_path)
         return txt_map

ultralytics/solutions/heatmap.py

@@ -124,6 +124,6 @@ class Heatmap(ObjectCounter):
             plot_im=plot_im,
             in_count=self.in_count,
             out_count=self.out_count,
-            classwise_count=dict(self.classwise_counts),
+            classwise_count=dict(self.classwise_count),
             total_tracks=len(self.track_ids),
         )

ultralytics/solutions/object_counter.py

@@ -43,7 +43,7 @@ class ObjectCounter(BaseSolution):
         self.in_count = 0  # Counter for objects moving inward
         self.out_count = 0  # Counter for objects moving outward
         self.counted_ids = []  # List of IDs of objects that have been counted
-        self.classwise_counts = defaultdict(lambda: {"IN": 0, "OUT": 0})  # Dictionary for counts, categorized by class
+        self.classwise_count = defaultdict(lambda: {"IN": 0, "OUT": 0})  # Dictionary for counts, categorized by class
         self.region_initialized = False  # Flag indicating whether the region has been initialized
 
         self.show_in = self.CFG["show_in"]
@@ -85,17 +85,17 @@ class ObjectCounter(BaseSolution):
                     # Vertical region: Compare x-coordinates to determine direction
                     if current_centroid[0] > prev_position[0]:  # Moving right
                         self.in_count += 1
-                        self.classwise_counts[self.names[cls]]["IN"] += 1
+                        self.classwise_count[self.names[cls]]["IN"] += 1
                     else:  # Moving left
                         self.out_count += 1
-                        self.classwise_counts[self.names[cls]]["OUT"] += 1
+                        self.classwise_count[self.names[cls]]["OUT"] += 1
                 # Horizontal region: Compare y-coordinates to determine direction
                 elif current_centroid[1] > prev_position[1]:  # Moving downward
                     self.in_count += 1
-                    self.classwise_counts[self.names[cls]]["IN"] += 1
+                    self.classwise_count[self.names[cls]]["IN"] += 1
                 else:  # Moving upward
                     self.out_count += 1
-                    self.classwise_counts[self.names[cls]]["OUT"] += 1
+                    self.classwise_count[self.names[cls]]["OUT"] += 1
                 self.counted_ids.append(track_id)
 
         elif len(self.region) > 2:  # Polygonal region
@@ -111,10 +111,10 @@ class ObjectCounter(BaseSolution):
                     and current_centroid[1] > prev_position[1]
                 ):  # Moving right or downward
                     self.in_count += 1
-                    self.classwise_counts[self.names[cls]]["IN"] += 1
+                    self.classwise_count[self.names[cls]]["IN"] += 1
                 else:  # Moving left or upward
                     self.out_count += 1
-                    self.classwise_counts[self.names[cls]]["OUT"] += 1
+                    self.classwise_count[self.names[cls]]["OUT"] += 1
                 self.counted_ids.append(track_id)
 
     def display_counts(self, plot_im) -> None:
@@ -132,7 +132,7 @@ class ObjectCounter(BaseSolution):
         labels_dict = {
             str.capitalize(key): f"{'IN ' + str(value['IN']) if self.show_in else ''} "
             f"{'OUT ' + str(value['OUT']) if self.show_out else ''}".strip()
-            for key, value in self.classwise_counts.items()
+            for key, value in self.classwise_count.items()
             if value["IN"] != 0 or value["OUT"] != 0 and (self.show_in or self.show_out)
         }
         if labels_dict:
@@ -190,6 +190,6 @@ class ObjectCounter(BaseSolution):
             plot_im=plot_im,
             in_count=self.in_count,
             out_count=self.out_count,
-            classwise_count=dict(self.classwise_counts),
+            classwise_count=dict(self.classwise_count),
             total_tracks=len(self.track_ids),
         )

ultralytics/solutions/solutions.py

@@ -808,10 +808,10 @@ class SolutionResults:
         filled_slots (int): The number of filled slots in a monitored area.
         email_sent (bool): A flag indicating whether an email notification was sent.
         total_tracks (int): The total number of tracked objects.
-        region_counts (Dict): The count of objects within a specific region.
+        region_counts (Dict[str, int]): The count of objects within a specific region.
         speed_dict (Dict[str, float]): A dictionary containing speed information for tracked objects.
         total_crop_objects (int): Total number of cropped objects using ObjectCropper class.
-        speed (Dict): Performance timing information for tracking and solution processing.
+        speed (Dict[str, float]): Performance timing information for tracking and solution processing.
     """
 
     def __init__(self, **kwargs):

ultralytics/utils/__init__.py

@@ -255,11 +255,8 @@ class DataExportMixin:
         Notes:
             Requires `lxml` package to be installed.
         """
-        from ultralytics.utils.checks import check_requirements
-
-        check_requirements("lxml")
         df = self.to_df(normalize=normalize, decimals=decimals)
-        return '<?xml version="1.0" encoding="utf-8"?>\n<root></root>' if df.empty else df.to_xml()
+        return '<?xml version="1.0" encoding="utf-8"?>\n<root></root>' if df.empty else df.to_xml(parser="etree")
 
     def to_html(self, normalize=False, decimals=5, index=False):
         """

ultralytics/utils/instance.py

@@ -406,6 +406,8 @@ class Instances:
                 | (self.keypoints[..., 1] < 0)
                 | (self.keypoints[..., 1] > h)
             ] = 0.0
+            self.keypoints[..., 0] = self.keypoints[..., 0].clip(0, w)
+            self.keypoints[..., 1] = self.keypoints[..., 1].clip(0, h)
 
     def remove_zero_area_boxes(self):
         """

ultralytics/utils/metrics.py

@@ -1078,23 +1078,21 @@ class DetMetrics(SimpleClass, DataExportMixin):
            >>> detection_summary = results.summary()
            >>> print(detection_summary)
         """
-        scalars = {
-            "box-map": round(self.box.map, decimals),
-            "box-map50": round(self.box.map50, decimals),
-            "box-map75": round(self.box.map75, decimals),
-        }
         per_class = {
-            "box-p": self.box.p,
-            "box-r": self.box.r,
-            "box-f1": self.box.f1,
+            "Box-P": self.box.p,
+            "Box-R": self.box.r,
+            "Box-F1": self.box.f1,
         }
         return [
             {
-                "class_name": self.names[self.ap_class_index[i]],
+                "Class": self.names[self.ap_class_index[i]],
+                "Images": self.nt_per_image[self.ap_class_index[i]],
+                "Instances": self.nt_per_class[self.ap_class_index[i]],
                 **{k: round(v[i], decimals) for k, v in per_class.items()},
-                **scalars,
+                "mAP50": round(self.class_result(i)[2], decimals),
+                "mAP50-95": round(self.class_result(i)[3], decimals),
             }
-            for i in range(len(per_class["box-p"]))
+            for i in range(len(per_class["Box-P"]))
         ]
 
 
@@ -1213,19 +1211,14 @@ class SegmentMetrics(DetMetrics):
             >>> seg_summary = results.summary(decimals=4)
             >>> print(seg_summary)
         """
-        scalars = {
-            "mask-map": round(self.seg.map, decimals),
-            "mask-map50": round(self.seg.map50, decimals),
-            "mask-map75": round(self.seg.map75, decimals),
-        }
         per_class = {
-            "mask-p": self.seg.p,
-            "mask-r": self.seg.r,
-            "mask-f1": self.seg.f1,
+            "Mask-P": self.seg.p,
+            "Mask-R": self.seg.r,
+            "Mask-F1": self.seg.f1,
         }
         summary = DetMetrics.summary(self, normalize, decimals)  # get box summary
         for i, s in enumerate(summary):
-            s.update({**{k: round(v[i], decimals) for k, v in per_class.items()}, **scalars})
+            s.update({**{k: round(v[i], decimals) for k, v in per_class.items()}})
         return summary
 
 
@@ -1357,19 +1350,14 @@ class PoseMetrics(DetMetrics):
             >>> pose_summary = results.summary(decimals=4)
             >>> print(pose_summary)
         """
-        scalars = {
-            "pose-map": round(self.pose.map, decimals),
-            "pose-map50": round(self.pose.map50, decimals),
-            "pose-map75": round(self.pose.map75, decimals),
-        }
         per_class = {
-            "pose-p": self.pose.p,
-            "pose-r": self.pose.r,
-            "pose-f1": self.pose.f1,
+            "Pose-P": self.pose.p,
+            "Pose-R": self.pose.r,
+            "Pose-F1": self.pose.f1,
         }
         summary = DetMetrics.summary(self, normalize, decimals)  # get box summary
         for i, s in enumerate(summary):
-            s.update({**{k: round(v[i], decimals) for k, v in per_class.items()}, **scalars})
+            s.update({**{k: round(v[i], decimals) for k, v in per_class.items()}})
         return summary
 
 
@@ -1445,7 +1433,7 @@ class ClassifyMetrics(SimpleClass, DataExportMixin):
             >>> classify_summary = results.summary(decimals=4)
             >>> print(classify_summary)
         """
-        return [{"classify-top1": round(self.top1, decimals), "classify-top5": round(self.top5, decimals)}]
+        return [{"top1_acc": round(self.top1, decimals), "top5_acc": round(self.top5, decimals)}]
 
 
 class OBBMetrics(DetMetrics):