ultralytics 8.3.24__py3-none-any.whl → 8.3.25__py3-none-any.whl

tests/test_exports.py

@@ -197,3 +197,10 @@ def test_export_ncnn():
     """Test YOLO exports to NCNN format."""
     file = YOLO(MODEL).export(format="ncnn", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
+
+
+@pytest.mark.slow
+def test_export_mnn():
+    """Test YOLO exports to MNN format."""
+    file = YOLO(MODEL).export(format="mnn", imgsz=32)
+    YOLO(file)(SOURCE, imgsz=32)  # exported model inference

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.24"
+__version__ = "8.3.25"
 
 import os
 

ultralytics/cfg/trackers/botsort.yaml

@@ -2,9 +2,9 @@
 # Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT
 
 tracker_type: botsort # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.5 # threshold for the first association
+track_high_thresh: 0.25 # threshold for the first association
 track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
+new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
 track_buffer: 30 # buffer to calculate the time when to remove tracks
 match_thresh: 0.8 # threshold for matching tracks
 fuse_score: True # Whether to fuse confidence scores with the iou distances before matching

ultralytics/cfg/trackers/bytetrack.yaml

@@ -2,9 +2,9 @@
 # Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack
 
 tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack']
-track_high_thresh: 0.5 # threshold for the first association
+track_high_thresh: 0.25 # threshold for the first association
 track_low_thresh: 0.1 # threshold for the second association
-new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
+new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
 track_buffer: 30 # buffer to calculate the time when to remove tracks
 match_thresh: 0.8 # threshold for matching tracks
 fuse_score: True # Whether to fuse confidence scores with the iou distances before matching

ultralytics/engine/exporter.py

@@ -16,6 +16,7 @@ TensorFlow Lite         | `tflite`                  | yolo11n.tflite
 TensorFlow Edge TPU     | `edgetpu`                 | yolo11n_edgetpu.tflite
 TensorFlow.js           | `tfjs`                    | yolo11n_web_model/
 PaddlePaddle            | `paddle`                  | yolo11n_paddle_model/
+MNN                     | `mnn`                     | yolo11n.mnn
 NCNN                    | `ncnn`                    | yolo11n_ncnn_model/
 
 Requirements:
@@ -41,6 +42,7 @@ Inference:
                          yolo11n.tflite             # TensorFlow Lite
                          yolo11n_edgetpu.tflite     # TensorFlow Edge TPU
                          yolo11n_paddle_model       # PaddlePaddle
+                         yolo11n.mnn                # MNN
                          yolo11n_ncnn_model         # NCNN
 
 TensorFlow.js:
@@ -109,6 +111,7 @@ def export_formats():
         ["TensorFlow Edge TPU", "edgetpu", "_edgetpu.tflite", True, False],
         ["TensorFlow.js", "tfjs", "_web_model", True, False],
         ["PaddlePaddle", "paddle", "_paddle_model", True, True],
+        ["MNN", "mnn", ".mnn", True, True],
         ["NCNN", "ncnn", "_ncnn_model", True, True],
     ]
     return dict(zip(["Format", "Argument", "Suffix", "CPU", "GPU"], zip(*x)))
@@ -190,7 +193,9 @@ class Exporter:
         flags = [x == fmt for x in fmts]
         if sum(flags) != 1:
             raise ValueError(f"Invalid export format='{fmt}'. Valid formats are {fmts}")
-        jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, ncnn = flags  # export booleans
+        jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, mnn, ncnn = (
+            flags  # export booleans
+        )
         is_tf_format = any((saved_model, pb, tflite, edgetpu, tfjs))
 
         # Device
@@ -333,8 +338,10 @@ class Exporter:
                 f[9], _ = self.export_tfjs()
         if paddle:  # PaddlePaddle
             f[10], _ = self.export_paddle()
+        if mnn:  # MNN
+            f[11], _ = self.export_mnn()
         if ncnn:  # NCNN
-            f[11], _ = self.export_ncnn()
+            f[12], _ = self.export_ncnn()
 
         # Finish
         f = [str(x) for x in f if x]  # filter out '' and None
@@ -541,6 +548,32 @@ class Exporter:
         yaml_save(Path(f) / "metadata.yaml", self.metadata)  # add metadata.yaml
         return f, None
 
+    @try_export
+    def export_mnn(self, prefix=colorstr("MNN:")):
+        """YOLOv8 MNN export using MNN https://github.com/alibaba/MNN."""
+        f_onnx, _ = self.export_onnx()  # get onnx model first
+
+        check_requirements("MNN>=2.9.6")
+        import MNN  # noqa
+        from MNN.tools import mnnconvert
+
+        # Setup and checks
+        LOGGER.info(f"\n{prefix} starting export with MNN {MNN.version()}...")
+        assert Path(f_onnx).exists(), f"failed to export ONNX file: {f_onnx}"
+        f = str(self.file.with_suffix(".mnn"))  # MNN model file
+        args = ["", "-f", "ONNX", "--modelFile", f_onnx, "--MNNModel", f, "--bizCode", json.dumps(self.metadata)]
+        if self.args.int8:
+            args.append("--weightQuantBits")
+            args.append("8")
+        if self.args.half:
+            args.append("--fp16")
+        mnnconvert.convert(args)
+        # remove scratch file for model convert optimize
+        convert_scratch = Path(self.file.parent / ".__convert_external_data.bin")
+        if convert_scratch.exists():
+            convert_scratch.unlink()
+        return f, None
+
     @try_export
     def export_ncnn(self, prefix=colorstr("NCNN:")):
         """YOLO NCNN export using PNNX https://github.com/pnnx/pnnx."""
@@ -890,8 +923,10 @@ class Exporter:
             tmp_file = f / "tmp_tflite_int8_calibration_images.npy"  # int8 calibration images file
             if self.args.data:
                 f.mkdir()
-                images = [batch["img"].permute(0, 2, 3, 1) for batch in self.get_int8_calibration_dataloader(prefix)]
-                images = torch.cat(images, 0).float()
+                images = [batch["img"] for batch in self.get_int8_calibration_dataloader(prefix)]
+                images = torch.nn.functional.interpolate(torch.cat(images, 0).float(), size=self.imgsz).permute(
+                    0, 2, 3, 1
+                )
                 np.save(str(tmp_file), images.numpy().astype(np.float32))  # BHWC
                 np_data = [["images", tmp_file, [[[[0, 0, 0]]]], [[[[255, 255, 255]]]]]]
 

ultralytics/engine/predictor.py

@@ -26,6 +26,7 @@ Usage - formats:
                               yolov8n.tflite             # TensorFlow Lite
                               yolov8n_edgetpu.tflite     # TensorFlow Edge TPU
                               yolov8n_paddle_model       # PaddlePaddle
+                              yolov8n.mnn                # MNN
                               yolov8n_ncnn_model         # NCNN
 """
 

ultralytics/engine/validator.py

@@ -17,6 +17,7 @@ Usage - formats:
                           yolov8n.tflite             # TensorFlow Lite
                           yolov8n_edgetpu.tflite     # TensorFlow Edge TPU
                           yolov8n_paddle_model       # PaddlePaddle
+                          yolov8n.mnn                # MNN
                           yolov8n_ncnn_model         # NCNN
 """
 

ultralytics/models/sam/modules/sam.py

@@ -854,6 +854,7 @@ class SAM2Model(torch.nn.Module):
         mask_inputs,
         output_dict,
         num_frames,
+        track_in_reverse,
         prev_sam_mask_logits,
     ):
         """Performs a single tracking step, updating object masks and memory features based on current frame inputs."""

ultralytics/nn/autobackend.py

@@ -59,21 +59,22 @@ class AutoBackend(nn.Module):
     range of formats, each with specific naming conventions as outlined below:
 
         Supported Formats and Naming Conventions:
-            | Format                | File Suffix      |
-            |-----------------------|------------------|
-            | PyTorch               | *.pt             |
-            | TorchScript           | *.torchscript    |
-            | ONNX Runtime          | *.onnx           |
-            | ONNX OpenCV DNN       | *.onnx (dnn=True)|
-            | OpenVINO              | *openvino_model/ |
-            | CoreML                | *.mlpackage      |
-            | TensorRT              | *.engine         |
-            | TensorFlow SavedModel | *_saved_model    |
-            | TensorFlow GraphDef   | *.pb             |
-            | TensorFlow Lite       | *.tflite         |
-            | TensorFlow Edge TPU   | *_edgetpu.tflite |
-            | PaddlePaddle          | *_paddle_model   |
-            | NCNN                  | *_ncnn_model     |
+            | Format                | File Suffix       |
+            |-----------------------|-------------------|
+            | PyTorch               | *.pt              |
+            | TorchScript           | *.torchscript     |
+            | ONNX Runtime          | *.onnx            |
+            | ONNX OpenCV DNN       | *.onnx (dnn=True) |
+            | OpenVINO              | *openvino_model/  |
+            | CoreML                | *.mlpackage       |
+            | TensorRT              | *.engine          |
+            | TensorFlow SavedModel | *_saved_model/    |
+            | TensorFlow GraphDef   | *.pb              |
+            | TensorFlow Lite       | *.tflite          |
+            | TensorFlow Edge TPU   | *_edgetpu.tflite  |
+            | PaddlePaddle          | *_paddle_model/   |
+            | MNN                   | *.mnn             |
+            | NCNN                  | *_ncnn_model/     |
 
     This class offers dynamic backend switching capabilities based on the input model format, making it easier to deploy
     models across various platforms.
@@ -120,6 +121,7 @@ class AutoBackend(nn.Module):
             edgetpu,
             tfjs,
             paddle,
+            mnn,
             ncnn,
             triton,
         ) = self._model_type(w)
@@ -189,10 +191,32 @@ class AutoBackend(nn.Module):
                 check_requirements("numpy==1.23.5")
             import onnxruntime
 
-            providers = ["CUDAExecutionProvider", "CPUExecutionProvider"] if cuda else ["CPUExecutionProvider"]
+            providers = onnxruntime.get_available_providers()
+            if not cuda and "CUDAExecutionProvider" in providers:
+                providers.remove("CUDAExecutionProvider")
+            elif cuda and "CUDAExecutionProvider" not in providers:
+                LOGGER.warning("WARNING ⚠️ Failed to start ONNX Runtime session with CUDA. Falling back to CPU...")
+                device = torch.device("cpu")
+                cuda = False
+            LOGGER.info(f"Preferring ONNX Runtime {providers[0]}")
             session = onnxruntime.InferenceSession(w, providers=providers)
             output_names = [x.name for x in session.get_outputs()]
             metadata = session.get_modelmeta().custom_metadata_map
+            dynamic = isinstance(session.get_outputs()[0].shape[0], str)
+            if not dynamic:
+                io = session.io_binding()
+                bindings = []
+                for output in session.get_outputs():
+                    y_tensor = torch.empty(output.shape, dtype=torch.float16 if fp16 else torch.float32).to(device)
+                    io.bind_output(
+                        name=output.name,
+                        device_type=device.type,
+                        device_id=device.index if cuda else 0,
+                        element_type=np.float16 if fp16 else np.float32,
+                        shape=tuple(y_tensor.shape),
+                        buffer_ptr=y_tensor.data_ptr(),
+                    )
+                    bindings.append(y_tensor)
 
         # OpenVINO
         elif xml:
@@ -381,6 +405,26 @@ class AutoBackend(nn.Module):
             output_names = predictor.get_output_names()
             metadata = w.parents[1] / "metadata.yaml"
 
+        # MNN
+        elif mnn:
+            LOGGER.info(f"Loading {w} for MNN inference...")
+            check_requirements("MNN")  # requires MNN
+            import os
+
+            import MNN
+
+            config = {}
+            config["precision"] = "low"
+            config["backend"] = "CPU"
+            config["numThread"] = (os.cpu_count() + 1) // 2
+            rt = MNN.nn.create_runtime_manager((config,))
+            net = MNN.nn.load_module_from_file(w, [], [], runtime_manager=rt, rearrange=True)
+
+            def torch_to_mnn(x):
+                return MNN.expr.const(x.data_ptr(), x.shape)
+
+            metadata = json.loads(net.get_info()["bizCode"])
+
         # NCNN
         elif ncnn:
             LOGGER.info(f"Loading {w} for NCNN inference...")
@@ -477,8 +521,22 @@ class AutoBackend(nn.Module):
 
         # ONNX Runtime
         elif self.onnx:
-            im = im.cpu().numpy()  # torch to numpy
-            y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
+            if self.dynamic:
+                im = im.cpu().numpy()  # torch to numpy
+                y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
+            else:
+                if not self.cuda:
+                    im = im.cpu()
+                self.io.bind_input(
+                    name="images",
+                    device_type=im.device.type,
+                    device_id=im.device.index if im.device.type == "cuda" else 0,
+                    element_type=np.float16 if self.fp16 else np.float32,
+                    shape=tuple(im.shape),
+                    buffer_ptr=im.data_ptr(),
+                )
+                self.session.run_with_iobinding(self.io)
+                y = self.bindings
 
         # OpenVINO
         elif self.xml:
@@ -554,6 +612,12 @@ class AutoBackend(nn.Module):
             self.predictor.run()
             y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names]
 
+        # MNN
+        elif self.mnn:
+            input_var = self.torch_to_mnn(im)
+            output_var = self.net.onForward([input_var])
+            y = [x.read() for x in output_var]
+
         # NCNN
         elif self.ncnn:
             mat_in = self.pyncnn.Mat(im[0].cpu().numpy())

ultralytics/utils/benchmarks.py

@@ -21,6 +21,7 @@ TensorFlow Lite         | `tflite`                  | yolov8n.tflite
 TensorFlow Edge TPU     | `edgetpu`                 | yolov8n_edgetpu.tflite
 TensorFlow.js           | `tfjs`                    | yolov8n_web_model/
 PaddlePaddle            | `paddle`                  | yolov8n_paddle_model/
+MNN                     | `mnn`                     | yolov8n.mnn
 NCNN                    | `ncnn`                    | yolov8n_ncnn_model/
 """
 
@@ -111,8 +112,8 @@ def benchmark(
                 assert not isinstance(model, YOLOWorld), "YOLOWorldv2 Paddle exports not supported yet"
                 assert not is_end2end, "End-to-end models not supported by PaddlePaddle yet"
                 assert LINUX or MACOS, "Windows Paddle exports not supported yet"
-            if i in {12}:  # NCNN
-                assert not isinstance(model, YOLOWorld), "YOLOWorldv2 NCNN exports not supported yet"
+            if i in {12, 13}:  # MNN, NCNN
+                assert not isinstance(model, YOLOWorld), "YOLOWorldv2 MNN, NCNN exports not supported yet"
             if "cpu" in device.type:
                 assert cpu, "inference not supported on CPU"
             if "cuda" in device.type:
@@ -132,7 +133,7 @@ def benchmark(
             assert model.task != "pose" or i != 7, "GraphDef Pose inference is not supported"
             assert i not in {9, 10}, "inference not supported"  # Edge TPU and TF.js are unsupported
             assert i != 5 or platform.system() == "Darwin", "inference only supported on macOS>=10.13"  # CoreML
-            if i in {12}:
+            if i in {13}:
                 assert not is_end2end, "End-to-end torch.topk operation is not supported for NCNN prediction yet"
             exported_model.predict(ASSETS / "bus.jpg", imgsz=imgsz, device=device, half=half)
 

ultralytics/utils/tuner.py

@@ -1,13 +1,16 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-import subprocess
-
 from ultralytics.cfg import TASK2DATA, TASK2METRIC, get_save_dir
 from ultralytics.utils import DEFAULT_CFG, DEFAULT_CFG_DICT, LOGGER, NUM_THREADS, checks
 
 
 def run_ray_tune(
-    model, space: dict = None, grace_period: int = 10, gpu_per_trial: int = None, max_samples: int = 10, **train_args
+    model,
+    space: dict = None,
+    grace_period: int = 10,
+    gpu_per_trial: int = None,
+    max_samples: int = 10,
+    **train_args,
 ):
     """
     Runs hyperparameter tuning using Ray Tune.
@@ -39,7 +42,7 @@ def run_ray_tune(
         train_args = {}
 
     try:
-        subprocess.run("pip install ray[tune]".split(), check=True)  # do not add single quotes here
+        checks.check_requirements("ray[tune]")
 
         import ray
         from ray import tune

{ultralytics-8.3.24.dist-info → ultralytics-8.3.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.24
+Version: 8.3.25
 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-8.3.24.dist-info → ultralytics-8.3.25.dist-info}/RECORD

@@ -3,11 +3,11 @@ tests/conftest.py,sha256=9PFAiwAy6eeORGspr5dOKxVuFDVKqYg8Nn_RxSJ27UI,2919
 tests/test_cli.py,sha256=G7OJ1ErQYsGy2Dx1zP-0p7EZR4aPoAdtLGiY4Hm7jQM,5006
 tests/test_cuda.py,sha256=rhHFvKNegN1ChtueKM0JhATJaJDFB377uXo2Kca5JVQ,5943
 tests/test_engine.py,sha256=dcEcJsMQh61rDSNv7l4TIAgybLpzjVwerv9JZC_KCM8,4934
-tests/test_exports.py,sha256=fpTKEVBUGLF3WiZPNKRs-IEcIY4cfxgvgKjUNfodjww,8042
+tests/test_exports.py,sha256=yYowGouJrMhvZXiklC8l4uq1R_p_Wy27RsmswklH93k,8243
 tests/test_integrations.py,sha256=f5-QCUk1SU_-qn4mBCZwS3GN3tXEBIIXo4z2EhExbHw,6126
 tests/test_python.py,sha256=I1RRdCwLdrc3jX06huVxct8HX8ccQOmQgVpuEflRl0U,23560
 tests/test_solutions.py,sha256=sPYhy2d814mIVvojQeVxeZPu0IVy01_Y8zuMcu_9GF0,3790
-ultralytics/__init__.py,sha256=e2H8k7jyu991EqE27QnJvrA-0fi4MKC_qARjJoT11TE,681
+ultralytics/__init__.py,sha256=YiWNN3uUV32CchAlJHPFiLwXwMrng7pwa5o0QKsf0ag,681
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=YXEtAr5WS3HLO90wFbyzspsaFxpBu4WJjVXWEFim-_o,32509
@@ -86,8 +86,8 @@ ultralytics/cfg/models/v9/yolov9m.yaml,sha256=l6CmivzNu44sRVmkQXk4-tXflbV1nWnk5M
 ultralytics/cfg/models/v9/yolov9s.yaml,sha256=lPWcu-6ub1kCBD6zIDFwthYZ3RvdJfODWKy3vEQWRjo,1291
 ultralytics/cfg/models/v9/yolov9t.yaml,sha256=qL__kr6GoefpQWP4jV0jdzwTp46bdFUcqtPRnfDbkY8,1275
 ultralytics/cfg/solutions/default.yaml,sha256=irtGM8nxaSBkrWMqcXoJdtKgqAq1YBwyVMGx5csSH2Y,1239
-ultralytics/cfg/trackers/botsort.yaml,sha256=8B0xNbnG_E-9DCUpap72PWkUgBb1AjuApEn7gHiVngE,916
-ultralytics/cfg/trackers/bytetrack.yaml,sha256=8vpTZ2x9mhRXJymoJvs1G8kTXo_HxbSwHup2FQALT3A,721
+ultralytics/cfg/trackers/botsort.yaml,sha256=FDIrZ3hAhRtMfDl654pt1HIexmPqlFQK-3lQ4D0tF84,918
+ultralytics/cfg/trackers/bytetrack.yaml,sha256=rBWY4RjjX6PTO2o6TUJFYHVgXNZHCN5TuBuzwuPYVjA,723
 ultralytics/data/__init__.py,sha256=VGe-ATG7j35F4A4r8Jmzffjlhve4JAJPgRa5ahKTU18,616
 ultralytics/data/annotator.py,sha256=oy87bzQN6ZRYeucoLk8e-jDEo6YJ91FE_zMFtLEVC1I,2489
 ultralytics/data/augment.py,sha256=YCLrwx1mRGeidggo_7GeINay8KdxACqREHJofZeaTHA,120430
@@ -99,13 +99,13 @@ ultralytics/data/loaders.py,sha256=Fr70Q9p9t7buLW_8R2_lI_nyCMG033gWSxvwy1M-a-U,2
 ultralytics/data/split_dota.py,sha256=eFafJ7Vg52wj6KDCHFJAf1tKzyPD5YaPB8kM4VX5Aeg,10688
 ultralytics/data/utils.py,sha256=bmWEIrdogj4kssZQSJdSbIF8QsJU00lo-EY-Mgcqv4M,31073
 ultralytics/engine/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8grmQDTs,42
-ultralytics/engine/exporter.py,sha256=TJsamX8n3JDFjVUiV9vmfAm-bOz09pMJnypgXYqbp5I,58735
+ultralytics/engine/exporter.py,sha256=atCOVnXPrN66xq1rbOTZFBQmY00qpveLrZ_C86DDZSc,60194
 ultralytics/engine/model.py,sha256=pvL1uf-wwdWL8Iph7VEAYn1-z7wEHzVug21V_0_gO6M,51456
-ultralytics/engine/predictor.py,sha256=keTelEeo23Dcbs-XvmRWAPIs4pbCNDtsMBz88WM1eK8,17534
+ultralytics/engine/predictor.py,sha256=aS4yJdTK2kYq-TTpzIlWxqnAcBz38zIECZoMb_yOPMY,17597
 ultralytics/engine/results.py,sha256=BxanBI8PhBCfs-9cSy-GS6naScuiD3hdvUAJWPW2mS0,75043
 ultralytics/engine/trainer.py,sha256=6dGOEZvMo3o97SLpKlcR5XmhWhUHh05uLYpj3jNn0jU,36981
 ultralytics/engine/tuner.py,sha256=WBj8iw1K1TK0hvanlA-wkwmfqh1SI8jEe2dGwUINeTg,11838
-ultralytics/engine/validator.py,sha256=2C_qXI36Z9rLOpmS0YR8Qe3ka4p23YiH2w5ai7-XBwE,14811
+ultralytics/engine/validator.py,sha256=aWpXE3nrOqaA7jCuUgwxi0FabiGTIXtZvjoJyCX903o,14870
 ultralytics/hub/__init__.py,sha256=c6Me4E8V-P7mtzTggyPYz9FnVkqWRyPp9F-fMcyFNQ0,5632
 ultralytics/hub/auth.py,sha256=pj_2NijotQpyG4_VJ6EAzNWGD93L6t-34J60yfiNZPc,5541
 ultralytics/hub/session.py,sha256=2KznO5kX14HFZ2-Ct9LoG312sdHuigQSLZb58MGvbJY,16411
@@ -136,7 +136,7 @@ ultralytics/models/sam/modules/blocks.py,sha256=Q-KwhFbdyZhl1tjG_kP2LcQkZbzoNt61
 ultralytics/models/sam/modules/decoders.py,sha256=mODsqnTN_CjE3H0Sh9cd8PfTnHANPjGB1bjqHxfezSg,25830
 ultralytics/models/sam/modules/encoders.py,sha256=Ay3sYeUonCf6URXBdB0dDwyngovevW8hUDgULRnNIoA,34824
 ultralytics/models/sam/modules/memory_attention.py,sha256=XilWBnRfH8wZxIoL2-yEk-dRypCsS0Jf_9t8WJxXKg0,9722
-ultralytics/models/sam/modules/sam.py,sha256=TEo4iB7i8B3hKr1SaNu-PDIWHl3FZoSvyjnSJZI0V1A,53076
+ultralytics/models/sam/modules/sam.py,sha256=H0EJpbwwYUJ-Hx4d_5OVCH0rZInmS937cu1183lzpcc,53102
 ultralytics/models/sam/modules/tiny_encoder.py,sha256=NyzeFMLnmqwcFQFs-JBM9PCWSsYoYZ_6h59Un1DeDV0,41332
 ultralytics/models/sam/modules/transformer.py,sha256=nuhF_14LGrr5uYCAP9XCXps-zlVcT4OWO0evXWDxPwI,16081
 ultralytics/models/sam/modules/utils.py,sha256=Y36V6BVy6GeaAvKE8gHmoDIa-f5LjJpmSVwywNkv2yk,12315
@@ -169,7 +169,7 @@ ultralytics/models/yolo/world/__init__.py,sha256=3VTH0q4NOt2EWRom15yCymvmvm0Etp2
 ultralytics/models/yolo/world/train.py,sha256=gaDrAmLJpg9qDtmL5evA5HsV2yb4RTRSfk2EDYrHdRg,3686
 ultralytics/models/yolo/world/train_world.py,sha256=IsnCEVt6DcM9lUskCKmIN-M8MM79xLpwTRqRoAHUnZ4,4857
 ultralytics/nn/__init__.py,sha256=4BPLHY89xEM_al5uK0aOmFgiML6CMGEZbezxOvTjOEs,587
-ultralytics/nn/autobackend.py,sha256=4KqKBafUP7SbsD6rtubukr2KhmYhTogLBSZtF3Hpjzc,31893
+ultralytics/nn/autobackend.py,sha256=as3IbpBeFM3YOAL5zGP3nu1EVVEiFsp3TwMfai55XCs,34618
 ultralytics/nn/tasks.py,sha256=NWe0cL7A0LpsP3S1Efvi2NutAjWc_rGYMJMwAeb2bAg,48605
 ultralytics/nn/modules/__init__.py,sha256=xhW2BennT9U_VaMXVpRu-bdLgp1BXt9L8mkIUBE3idU,2625
 ultralytics/nn/modules/activation.py,sha256=chhn469wnRHEs5BMGNBYXwPYZc_7-urspTT8fnBd-xA,895
@@ -200,7 +200,7 @@ ultralytics/trackers/utils/kalman_filter.py,sha256=cH9zD3fwkuezP97H9mw8cSBN7a8hH
 ultralytics/trackers/utils/matching.py,sha256=3Ie1WNNRZ4_q3365F03XD7Nr9juZB_08mw4yUKC3w74,7162
 ultralytics/utils/__init__.py,sha256=oUtiHZUVtz-KtequUv15Has85k2BHgP6c-_cAAdf-rM,49060
 ultralytics/utils/autobatch.py,sha256=BO9MCRtrLDtrDQaxqV0BdjaYsgXf-q07Y3_VdGp4URY,4330
-ultralytics/utils/benchmarks.py,sha256=R3_jtwLd48azPSXmtIhqlzduUvflk0FOY8GJOJ6mB6E,25097
+ultralytics/utils/benchmarks.py,sha256=UVjTO1gRCNVdk1-meSeNAh050nWhIR7i5E3ZjRcdyPk,25177
 ultralytics/utils/checks.py,sha256=cEQIYK3ZGQqcQ9uckNF-KbYdjGpfA1FHJHsUim94EoA,29800
 ultralytics/utils/dist.py,sha256=NDFga-uKxkBX2zLxFHSene_cCiGQJoyOeCXcN9JIOIk,2358
 ultralytics/utils/downloads.py,sha256=fh7I5toTSowAOXtmx5zIzCEDREfTFG45cLIHmsDmuYw,21974
@@ -215,7 +215,7 @@ ultralytics/utils/plotting.py,sha256=TKtdbAOl6gZdFD2hlA5T4LNWfr2LUWbCC-cXkgL1JAU
 ultralytics/utils/tal.py,sha256=ECsu95xEqOItmxMDN4YTD3FsUiIsQNWy0pZC3TfvFfk,16877
 ultralytics/utils/torch_utils.py,sha256=91fmJtZRvIVb6LI-wNkNrlHE7mMNBmcR4oif8ZYppYU,30089
 ultralytics/utils/triton.py,sha256=gg1finxno_tY2Ge9PMhmu7PI9wvoFZoiicdT4Bhqv3w,3936
-ultralytics/utils/tuner.py,sha256=mJdgvuE2StoFS13mEdsTbsxQgSZA4fSdSCgoyh8PvNw,6250
+ultralytics/utils/tuner.py,sha256=K09-z5k1E4ZriSKoWdwQrJ2PJ2fY1ez3-b2R6aKPTqM,6198
 ultralytics/utils/callbacks/__init__.py,sha256=YrWqC3BVVaTLob4iCPR6I36mUxIUOpPJW7B_LjT78Qw,214
 ultralytics/utils/callbacks/base.py,sha256=PHjQ6RITwC2dylCQTB0bdPgAsHjxVeuDb5N1NPTbHGc,5775
 ultralytics/utils/callbacks/clearml.py,sha256=qbLbqzMVWAnjqg5YUM-Ue6CmGueFCvqKpHFKlw-MyVc,5933
@@ -227,9 +227,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=IbGQfEltamUKXJt93uSLQFn8c2rYh3DMTg
 ultralytics/utils/callbacks/raytune.py,sha256=ODVYzy-CoM4Uge0zjkh3Hnh9nF2M0vhDrSenXnvcizw,705
 ultralytics/utils/callbacks/tensorboard.py,sha256=SHlE58Fb-sg-uZKtgy-ybIO3SAIfK55aj8kTYGA0Cyg,4167
 ultralytics/utils/callbacks/wb.py,sha256=oX3JarCJGhzvW556XiEXQNaZblAaK_UETAt3kzkY61w,6869
-ultralytics-8.3.24.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.24.dist-info/METADATA,sha256=NkjGa5lIXR6fh71OxXnh155XCqvuZGz6qDihMM_bX4g,35081
-ultralytics-8.3.24.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-ultralytics-8.3.24.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.24.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.24.dist-info/RECORD,,
+ultralytics-8.3.25.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.25.dist-info/METADATA,sha256=l2ixBYS0H21g6Nn7iGFLQZxuptNlobGD_PJY7AQTfGg,35081
+ultralytics-8.3.25.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+ultralytics-8.3.25.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.25.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.25.dist-info/RECORD,,

{ultralytics-8.3.24.dist-info → ultralytics-8.3.25.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any