ultralytics 8.3.122__py3-none-any.whl → 8.3.123__py3-none-any.whl

tests/test_cuda.py

@@ -115,7 +115,7 @@ def test_utils_benchmarks():
 
     # Pre-export a dynamic engine model to use dynamic inference
     YOLO(MODEL).export(format="engine", imgsz=32, dynamic=True, batch=1)
-    ProfileModels([MODEL], imgsz=32, half=False, min_time=1, num_timed_runs=3, num_warmup_runs=1).profile()
+    ProfileModels([MODEL], imgsz=32, half=False, min_time=1, num_timed_runs=3, num_warmup_runs=1).run()
 
 
 @pytest.mark.skipif(not CUDA_IS_AVAILABLE, reason="CUDA is not available")

tests/test_python.py

@@ -399,18 +399,18 @@ def test_utils_benchmarks():
     """Benchmark model performance using 'ProfileModels' from 'ultralytics.utils.benchmarks'."""
     from ultralytics.utils.benchmarks import ProfileModels
 
-    ProfileModels(["yolo11n.yaml"], imgsz=32, min_time=1, num_timed_runs=3, num_warmup_runs=1).profile()
+    ProfileModels(["yolo11n.yaml"], imgsz=32, min_time=1, num_timed_runs=3, num_warmup_runs=1).run()
 
 
 def test_utils_torchutils():
     """Test Torch utility functions including profiling and FLOP calculations."""
     from ultralytics.nn.modules.conv import Conv
-    from ultralytics.utils.torch_utils import get_flops_with_torch_profiler, profile, time_sync
+    from ultralytics.utils.torch_utils import get_flops_with_torch_profiler, profile_ops, time_sync
 
     x = torch.randn(1, 64, 20, 20)
     m = Conv(64, 64, k=1, s=2)
 
-    profile(x, [m], n=3)
+    profile_ops(x, [m], n=3)
     get_flops_with_torch_profiler(m)
     time_sync()
 

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.122"
+__version__ = "8.3.123"
 
 import os
 

ultralytics/engine/exporter.py

@@ -140,7 +140,7 @@ def export_formats():
         ["MNN", "mnn", ".mnn", True, True, ["batch", "half", "int8"]],
         ["NCNN", "ncnn", "_ncnn_model", True, True, ["batch", "half"]],
         ["IMX", "imx", "_imx_model", True, True, ["int8", "fraction"]],
-        ["RKNN", "rknn", "_rknn_model", False, False, ["batch", "name"]],
+        ["RKNN", "rknn", "_rknn_model", False, False, ["batch", "name", "int8"]],
     ]
     return dict(zip(["Format", "Argument", "Suffix", "CPU", "GPU", "Arguments"], zip(*x)))
 
@@ -970,8 +970,9 @@ class Exporter:
             output_integer_quantized_tflite=self.args.int8,
             quant_type="per-tensor",  # "per-tensor" (faster) or "per-channel" (slower but more accurate)
             custom_input_op_name_np_data_path=np_data,
-            disable_group_convolution=True,  # for end-to-end model compatibility
-            enable_batchmatmul_unfold=True,  # for end-to-end model compatibility
+            enable_batchmatmul_unfold=True,  # fix lower no. of detected objects on GPU delegate
+            output_signaturedefs=True,  # fix error with Attention block group convolution
+            optimization_for_gpu_delegate=True,
         )
         yaml_save(f / "metadata.yaml", self.metadata)  # add metadata.yaml
 
@@ -1110,8 +1111,8 @@ class Exporter:
         rknn = RKNN(verbose=False)
         rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform=self.args.name)
         rknn.load_onnx(model=f)
-        rknn.build(do_quantization=False)  # TODO: Add quantization support
-        f = f.replace(".onnx", f"-{self.args.name}.rknn")
+        rknn.build(do_quantization=self.args.int8)
+        f = f.replace(".onnx", f"-{self.args.name}-int8.rknn" if self.args.int8 else f"-{self.args.name}-fp16.rknn")
         rknn.export_rknn(f"{export_path / f}")
         yaml_save(export_path / "metadata.yaml", self.metadata)
         return export_path, None

ultralytics/engine/results.py

@@ -662,17 +662,14 @@ class Results(SimpleClass):
             - For classification tasks, it returns the top 5 class probabilities and their corresponding class names.
             - The returned string is comma-separated and ends with a comma and a space.
         """
-        log_string = ""
         probs = self.probs
         if len(self) == 0:
-            return log_string if probs is not None else f"{log_string}(no detections), "
+            return "" if probs is not None else "(no detections), "
         if probs is not None:
-            log_string += f"{', '.join(f'{self.names[j]} {probs.data[j]:.2f}' for j in probs.top5)}, "
+            return f"{', '.join(f'{self.names[j]} {probs.data[j]:.2f}' for j in probs.top5)}, "
         if boxes := self.boxes:
-            for c in boxes.cls.unique():
-                n = (boxes.cls == c).sum()  # detections per class
-                log_string += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "
-        return log_string
+            counts = boxes.cls.int().bincount()
+            return "".join(f"{n} {self.names[i]}{'s' * (n > 1)}, " for i, n in enumerate(counts) if n > 0)
 
     def save_txt(self, txt_file, save_conf=False):
         """

ultralytics/models/yolo/detect/predict.py

@@ -90,7 +90,7 @@ class DetectionPredictor(BasePredictor):
         obj_feats = torch.cat(
             [x.permute(0, 2, 3, 1).reshape(x.shape[0], -1, s, x.shape[1] // s).mean(dim=-1) for x in feat_maps], dim=1
         )  # mean reduce all vectors to same length
-        return [feats[idx] for feats, idx in zip(obj_feats, idxs)]  # for each image in batch, indexed separately
+        return [feats[idx] if len(idx) else [] for feats, idx in zip(obj_feats, idxs)]  # for each img in batch
 
     def construct_results(self, preds, img, orig_imgs):
         """

ultralytics/nn/autobackend.py

@@ -725,7 +725,7 @@ class AutoBackend(nn.Module):
         else:
             im = im.cpu().numpy()
             if self.saved_model:  # SavedModel
-                y = self.model(im, training=False) if self.keras else self.model(im)
+                y = self.model(im, training=False) if self.keras else self.model.serving_default(im)
                 if not isinstance(y, list):
                     y = [y]
             elif self.pb:  # GraphDef

ultralytics/trackers/track.py

@@ -58,10 +58,10 @@ def on_predict_start(predictor: object, persist: bool = False) -> None:
             predictor._feats = None
 
             # Register hook to extract input of Detect layer
-            def capture_io(module, input, output):
-                predictor._feats = input[0]
+            def pre_hook(module, input):
+                predictor._feats = [t.clone() for t in input[0]]
 
-            predictor.model.model.model[-1].register_forward_hook(capture_io)
+            predictor.model.model.model[-1].register_forward_pre_hook(pre_hook)
 
     trackers = []
     for _ in range(predictor.dataset.bs):

ultralytics/utils/autobatch.py

@@ -8,7 +8,7 @@ import numpy as np
 import torch
 
 from ultralytics.utils import DEFAULT_CFG, LOGGER, colorstr
-from ultralytics.utils.torch_utils import autocast, profile
+from ultralytics.utils.torch_utils import autocast, profile_ops
 
 
 def check_train_batch_size(model, imgsz=640, amp=True, batch=-1, max_num_obj=1):
@@ -74,7 +74,7 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch, max
     batch_sizes = [1, 2, 4, 8, 16] if t < 16 else [1, 2, 4, 8, 16, 32, 64]
     try:
         img = [torch.empty(b, 3, imgsz, imgsz) for b in batch_sizes]
-        results = profile(img, model, n=1, device=device, max_num_obj=max_num_obj)
+        results = profile_ops(img, model, n=1, device=device, max_num_obj=max_num_obj)
 
         # Fit a solution
         xy = [

ultralytics/utils/benchmarks.py

@@ -4,7 +4,7 @@ Benchmark a YOLO model formats for speed and accuracy.
 
 Usage:
     from ultralytics.utils.benchmarks import ProfileModels, benchmark
-    ProfileModels(['yolo11n.yaml', 'yolov8s.yaml']).profile()
+    ProfileModels(['yolo11n.yaml', 'yolov8s.yaml']).run()
     benchmark(model='yolo11n.pt', imgsz=160)
 
 Format                  | `format=argument`         | Model
@@ -378,7 +378,7 @@ class ProfileModels:
         Profile models and print results
         >>> from ultralytics.utils.benchmarks import ProfileModels
         >>> profiler = ProfileModels(["yolo11n.yaml", "yolov8s.yaml"], imgsz=640)
-        >>> profiler.profile()
+        >>> profiler.run()
     """
 
     def __init__(
@@ -412,7 +412,7 @@ class ProfileModels:
             Initialize and profile models
             >>> from ultralytics.utils.benchmarks import ProfileModels
             >>> profiler = ProfileModels(["yolo11n.yaml", "yolov8s.yaml"], imgsz=640)
-            >>> profiler.profile()
+            >>> profiler.run()
         """
         self.paths = paths
         self.num_timed_runs = num_timed_runs
@@ -423,7 +423,7 @@ class ProfileModels:
         self.trt = trt  # run TensorRT profiling
         self.device = device or torch.device(0 if torch.cuda.is_available() else "cpu")
 
-    def profile(self):
+    def run(self):
         """
         Profile YOLO models for speed and accuracy across various formats including ONNX and TensorRT.
 
@@ -434,7 +434,7 @@ class ProfileModels:
             Profile models and print results
             >>> from ultralytics.utils.benchmarks import ProfileModels
             >>> profiler = ProfileModels(["yolo11n.yaml", "yolov8s.yaml"])
-            >>> results = profiler.profile()
+            >>> results = profiler.run()
         """
         files = self.get_files()
 

ultralytics/utils/torch_utils.py

@@ -378,7 +378,7 @@ def model_info_for_loggers(trainer):
     if trainer.args.profile:  # profile ONNX and TensorRT times
         from ultralytics.utils.benchmarks import ProfileModels
 
-        results = ProfileModels([trainer.last], device=trainer.device).profile()[0]
+        results = ProfileModels([trainer.last], device=trainer.device).run()[0]
         results.pop("model/name")
     else:  # only return PyTorch times from most recent validation
         results = {
@@ -790,7 +790,7 @@ def cuda_memory_usage(device=None):
         yield cuda_info
 
 
-def profile(input, ops, n=10, device=None, max_num_obj=0):
+def profile_ops(input, ops, n=10, device=None, max_num_obj=0):
     """
     Ultralytics speed, memory and FLOPs profiler.
 
@@ -805,11 +805,11 @@ def profile(input, ops, n=10, device=None, max_num_obj=0):
         (list): Profile results for each operation.
 
     Examples:
-        >>> from ultralytics.utils.torch_utils import profile
+        >>> from ultralytics.utils.torch_utils import profile_ops
         >>> input = torch.randn(16, 3, 640, 640)
         >>> m1 = lambda x: x * torch.sigmoid(x)
         >>> m2 = nn.SiLU()
-        >>> profile(input, [m1, m2], n=100)  # profile over 100 iterations
+        >>> profile_ops(input, [m1, m2], n=100)  # profile over 100 iterations
     """
     results = []
     if not isinstance(device, torch.device):

{ultralytics-8.3.122.dist-info → ultralytics-8.3.123.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.122
+Version: 8.3.123
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{ultralytics-8.3.122.dist-info → ultralytics-8.3.123.dist-info}/RECORD

@@ -1,13 +1,13 @@
 tests/__init__.py,sha256=xnMhv3O_DF1YrW4zk__ZywQzAaoTDjPKPoiI1Ktss1w,670
 tests/conftest.py,sha256=rsIAipRKfrVNoTaJ1LdpYue8AbcJ_fr3d3WIlM_6uXY,2982
 tests/test_cli.py,sha256=PtMFl5Lp_6ygBbYDJ1ndofz2k7ZYupMPEAiZw6aZVm8,5450
-tests/test_cuda.py,sha256=0uvTF4bY_Grsd_Xgtp7TdIEgMpUqKv8_kWA82NYDl_g,6260
+tests/test_cuda.py,sha256=vCpPMAkEUQrQMVe4oMwGZQVOiuujEAkZ2zturNXFF-4,6256
 tests/test_engine.py,sha256=aGqZ8P7QO5C_nOa1b4FOyk92Ysdk5WiP-ST310Vyxys,4962
 tests/test_exports.py,sha256=dhZn86LdbapW15RthQF870LGxDjC1MUZhlGdBgPmgIQ,9716
 tests/test_integrations.py,sha256=dQteeRsRVuT_p5-T88-7jqT65Zm9iAXkyKg-KQ1_TQ8,6341
-tests/test_python.py,sha256=ok2xp7zwPOwcyl4yNawlx1uJ5HETn9eU-jyTPYzA0fI,25491
+tests/test_python.py,sha256=NDIqkKt-awgjq45y29xopZLhX8kkknqYz81Wm7ixqXo,25495
 tests/test_solutions.py,sha256=BIvg9zW0a_ggEmrPKgB_Y0MncveH-eYuN5KlqdJ6nHs,5726
-ultralytics/__init__.py,sha256=StjzKKqUrYk4rkeEY2AnsNAR8keYsHJzELLBKmqs6Q4,730
+ultralytics/__init__.py,sha256=FzBnkV__4DhnrF8Rs0JzvAR9A3VOlusTeRBaIY30-Do,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=ZXbvd-lyu0IIwVYAN6NH3KbQ5MLC5865Lh2c7IDkNSw,39675
@@ -118,10 +118,10 @@ 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=rFi7V-REi66DRLTWQzgx87NMfdp8eLfPZkYfSpS7Wfg,70137
+ultralytics/engine/exporter.py,sha256=56PU45SvNhYym9JiJctZXO5NkW-cwzTu5o7yIqx13Fc,70251
 ultralytics/engine/model.py,sha256=wS1cwgv0iyhsslMAZYMGlYDWitDIRW96d7MxwW-Sw5o,52817
 ultralytics/engine/predictor.py,sha256=YJ5l-0qIpr6JAJxowswtZ0IqmXBqVTvAA9vR40v0sCM,21752
-ultralytics/engine/results.py,sha256=MZkhI0CCOkBQPR-EzswymVqvqeyk35EkESGUQ_08r8k,79738
+ultralytics/engine/results.py,sha256=-JPBn_YMyZv6HhdlyhjRIZCcMf41LTyWID7JrEP64rc,79632
 ultralytics/engine/trainer.py,sha256=fdB8H6brnnQAL-ZFP6nmNmKMze0_qy0OT3jJg1B5uhQ,38864
 ultralytics/engine/tuner.py,sha256=IyFKsh4Q4a1DsjfK02DdN9cufAiBDhdhIq7F7ddguys,12646
 ultralytics/engine/validator.py,sha256=jfV81wuFDgrVVXEcPzgOpxAPrAZn-1LgpKwu9l_1-ts,17050
@@ -169,7 +169,7 @@ ultralytics/models/yolo/classify/predict.py,sha256=JV9szginTQ9Lpob0FozhKMiEIu1vV
 ultralytics/models/yolo/classify/train.py,sha256=rv2CJv9fzvtHf2q4l5g0RsjplWKeLpz637kKqjtrLNY,9737
 ultralytics/models/yolo/classify/val.py,sha256=xk-YwSQdl_oqyCBV0OOAOcXFL6CchebFOc36AkRSyjE,9992
 ultralytics/models/yolo/detect/__init__.py,sha256=GIRsLYR-kT4JJx7lh4ZZAFGBZj0aebokuU0A7JbjDVA,257
-ultralytics/models/yolo/detect/predict.py,sha256=oAftDYhksUDjVfgKIsmmair1_ujwVY-yc-MHrl7r9Hw,5343
+ultralytics/models/yolo/detect/predict.py,sha256=n1-WmzkvW3dHglI7XrxDr4i0nZ236h6Wh37TAWXpFfo,5341
 ultralytics/models/yolo/detect/train.py,sha256=YOEmUZkfJBq6hNbB_P10k-uy4_2fUgdPfVWzO4y8Egs,9538
 ultralytics/models/yolo/detect/val.py,sha256=7AB_wZi7aQ9_V1pZQSWk5qiJYS34fuO3P5aX7_3eeFE,18471
 ultralytics/models/yolo/obb/__init__.py,sha256=tQmpG8wVHsajWkZdmD6cjGohJ4ki64iSXQT8JY_dydo,221
@@ -193,7 +193,7 @@ ultralytics/models/yolo/yoloe/train.py,sha256=St3zw_XWRol9pODWU4lvKlJnWYr1lmWQNu
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=l0SOMQQd0Y_EBBHhTNekgrQsftqhYyK4oWTdCg1dLrE,4633
 ultralytics/models/yolo/yoloe/val.py,sha256=oA8cVT3pBXF6aPZy7ITq0mDcktRuIgks8tTtqMRISyY,8431
 ultralytics/nn/__init__.py,sha256=rjociYD9lo_K-d-1s6TbdWklPLjTcEHk7OIlRDJstIE,615
-ultralytics/nn/autobackend.py,sha256=tnYxzboWGBgNvUYrz2zokPH1Bw__GD2ZQro1gO-ZIF8,39298
+ultralytics/nn/autobackend.py,sha256=ng6CUi82BrV6qGVsif_U_1E4foL19N7isB7tQGECTGE,39314
 ultralytics/nn/tasks.py,sha256=EwRC70qA3eP8Xp-gGP8OuN-q8LCGDrq1iRue7ncRSV4,62916
 ultralytics/nn/text_model.py,sha256=8_7SRejKZA4Pi-ha0gjcWrQDDCDMBhtwlg8pPMWgjDE,13145
 ultralytics/nn/modules/__init__.py,sha256=dXLtIk9rt944WfsTdpgEdWOg3HQEHdwQztuZ6WNJygs,3144
@@ -225,14 +225,14 @@ ultralytics/trackers/__init__.py,sha256=Zlu_Ig5osn7hqch_g5Be_e4pwZUkeeTQiesJCi0p
 ultralytics/trackers/basetrack.py,sha256=LYvWB5d7Woyrz_RlxaopjV07RQKH3sff_lZJfMcMxcA,4450
 ultralytics/trackers/bot_sort.py,sha256=rpaj7X8COT0Vi5GFR9z-CGSBgJ7gTfFx2wTSZFTnhco,11466
 ultralytics/trackers/byte_tracker.py,sha256=D7JQ_6V8OUMQryxTrAr010UXMSaboQnI7T1xppzHXYg,20921
-ultralytics/trackers/track.py,sha256=mu6L9RWAW8Nq0vJanX-hTTUST-OmLq49d8VV96-J9u8,4817
+ultralytics/trackers/track.py,sha256=wuja3-xceuhaTEJyD2VqRBJUodPEM7-4iK47MkxshjM,4830
 ultralytics/trackers/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
 ultralytics/trackers/utils/gmc.py,sha256=dz3I5LbIv7h1__Xg7rGHecQFE32VFTe54tUnxb8F0Z8,14466
 ultralytics/trackers/utils/kalman_filter.py,sha256=A0CqOnnaKH6kr0XwuHzyHmIU6aJAjJYxF9jVlNBKZHo,21326
 ultralytics/trackers/utils/matching.py,sha256=7eIufSdeN7cXuFMjvcfvz0Ldq84m4YKZl5IGxBR8IIo,7169
 ultralytics/utils/__init__.py,sha256=qV5nw3ED1NuSCoYwW3WpT6BTLeCnoH7KJgbPZU_3Sbo,50422
-ultralytics/utils/autobatch.py,sha256=VZTIKLWeFZFwBHJmbiCn3MaxoFp89hLR0DSCR_iLXJg,4913
-ultralytics/utils/benchmarks.py,sha256=aZse9tetEwjMy2GkdNWZ0WfCgjLfCM3_BkI1qNNQb_w,30377
+ultralytics/utils/autobatch.py,sha256=kg05q2qKg74y_Uq2vvr01i3KhLfpVR7sT0IXBt3_kyI,4921
+ultralytics/utils/benchmarks.py,sha256=GXcatQqAUCBg3lSmzR5ZEZDYWdPREtFapHP-S4wj7G4,30357
 ultralytics/utils/checks.py,sha256=5bkna--ZH4FJDZtgef_K4xgjiKOZqCarTqIE4Z0vwJU,32628
 ultralytics/utils/dist.py,sha256=e-DK_YowV7D9rDGQyWR9Kaosxp2eWe2EogSWnnUMthc,4098
 ultralytics/utils/downloads.py,sha256=IvHng2-bApoyi-QMvesGwMmFNqEFiXPIKiiW16Q-U4M,22220
@@ -246,7 +246,7 @@ ultralytics/utils/ops.py,sha256=YFwPrKlPcgEmgAWqnJVR0Ccx5NQgp5e3P-YYHwVSP0k,3477
 ultralytics/utils/patches.py,sha256=6rVT-l8WDp_Py3O-gZdv9t3PnrYRRkrX_lF3mZ1XS8c,4928
 ultralytics/utils/plotting.py,sha256=5QPK1y-gm4T1mK3sjfRZhIUJAyP05D1cJ7h9wHPTifU,46616
 ultralytics/utils/tal.py,sha256=P5nPoR9qNnFuDIda0fsn8WP6m1V8r7EbvXUuhNRFFTA,20805
-ultralytics/utils/torch_utils.py,sha256=KUt2qoud3O2bb_cWv1TDjZloNKuLbWk0XJU97wlEdU4,39028
+ultralytics/utils/torch_utils.py,sha256=iaf7aJaZUadjBRvOs0vN2iIEePXIE8024anUOVkxPqE,39036
 ultralytics/utils/triton.py,sha256=xK9Db_ZUVDnIK1u76S2G-6ulIBsLfj9HN_YOaSrnMuU,5304
 ultralytics/utils/tuner.py,sha256=0Bp7l5dWZe1RzdvAIa11wQoX6eoAaoNRcA-EAnpofbk,6755
 ultralytics/utils/callbacks/__init__.py,sha256=hzL63Rce6VkZhP4Lcim9LKjadixaQG86nKqPhk7IkS0,242
@@ -260,9 +260,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=JaI95Cj2kIjUhlEEOiDN0-Drc-fDelLhNI
 ultralytics/utils/callbacks/raytune.py,sha256=A8amUGpux7dYES-L1iSeMoMXBySGWCD1aUqT7vcG-pU,1284
 ultralytics/utils/callbacks/tensorboard.py,sha256=jgYnym3cUQFAgN1GzTyO7l3jINtfAh8zhrllDvnLuVQ,5339
 ultralytics/utils/callbacks/wb.py,sha256=iDRFXI4IIDm8R5OI89DMTmjs8aHLo1HRCLkOFKdaMG4,7507
-ultralytics-8.3.122.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.122.dist-info/METADATA,sha256=Ie20iTid09rrSu0IDpyAHcgvr6MlwsZqZ5ciNuwfWmM,37180
-ultralytics-8.3.122.dist-info/WHEEL,sha256=wXxTzcEDnjrTwFYjLPcsW_7_XihufBwmpiBeiXNBGEA,91
-ultralytics-8.3.122.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.122.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.122.dist-info/RECORD,,
+ultralytics-8.3.123.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.123.dist-info/METADATA,sha256=kC_n3rFeiSOMo5st7xOemdh851cEtByxNnwucTt52_s,37180
+ultralytics-8.3.123.dist-info/WHEEL,sha256=wXxTzcEDnjrTwFYjLPcsW_7_XihufBwmpiBeiXNBGEA,91
+ultralytics-8.3.123.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.123.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.123.dist-info/RECORD,,