ultralytics 8.3.118__py3-none-any.whl → 8.3.120__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.118"
+__version__ = "8.3.120"
 
 import os
 

ultralytics/cfg/__init__.py

@@ -181,6 +181,7 @@ CFG_FRACTION_KEYS = frozenset(
         "bgr",
         "mosaic",
         "mixup",
+        "cutmix",
         "copy_paste",
         "conf",
         "iou",

ultralytics/cfg/default.yaml

@@ -114,6 +114,7 @@ fliplr: 0.5 # (float) image flip left-right (probability)
 bgr: 0.0 # (float) image channel BGR (probability)
 mosaic: 1.0 # (float) image mosaic (probability)
 mixup: 0.0 # (float) image mixup (probability)
+cutmix: 0.0 # (float) image cutmix (probability)
 copy_paste: 0.0 # (float) segment copy-paste (probability)
 copy_paste_mode: "flip" # (str) the method to do copy_paste augmentation (flip, mixup)
 auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix)

ultralytics/data/augment.py

@@ -317,7 +317,7 @@ class Compose:
 
 class BaseMixTransform:
     """
-    Base class for mix transformations like MixUp and Mosaic.
+    Base class for mix transformations like Cutmix, MixUp and Mosaic.
 
     This class provides a foundation for implementing mix transformations on datasets. It handles the
     probability-based application of transforms and manages the mixing of multiple images and labels.
@@ -348,7 +348,7 @@ class BaseMixTransform:
 
     def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
         """
-        Initializes the BaseMixTransform object for mix transformations like MixUp and Mosaic.
+        Initializes the BaseMixTransform object for mix transformations like CutMix, MixUp and Mosaic.
 
         This class serves as a base for implementing mix transformations in image processing pipelines.
 
@@ -368,7 +368,7 @@ class BaseMixTransform:
 
     def __call__(self, labels):
         """
-        Applies pre-processing transforms and mixup/mosaic transforms to labels data.
+        Applies pre-processing transforms and cutmix/mixup/mosaic transforms to labels data.
 
         This method determines whether to apply the mix transform based on a probability factor. If applied, it
         selects additional images, applies pre-transforms if specified, and then performs the mix transform.
@@ -391,7 +391,7 @@ class BaseMixTransform:
         if isinstance(indexes, int):
             indexes = [indexes]
 
-        # Get images information will be used for Mosaic or MixUp
+        # Get images information will be used for Mosaic, CutMix or MixUp
         mix_labels = [self.dataset.get_image_and_label(i) for i in indexes]
 
         if self.pre_transform is not None:
@@ -401,16 +401,16 @@ class BaseMixTransform:
 
         # Update cls and texts
         labels = self._update_label_text(labels)
-        # Mosaic or MixUp
+        # Mosaic, CutMix or MixUp
         labels = self._mix_transform(labels)
         labels.pop("mix_labels", None)
         return labels
 
     def _mix_transform(self, labels):
         """
-        Applies MixUp or Mosaic augmentation to the label dictionary.
+        Applies CutMix, MixUp or Mosaic augmentation to the label dictionary.
 
-        This method should be implemented by subclasses to perform specific mix transformations like MixUp or
+        This method should be implemented by subclasses to perform specific mix transformations like CutMix, MixUp or
         Mosaic. It modifies the input label dictionary in-place with the augmented data.
 
         Args:
@@ -439,7 +439,7 @@ class BaseMixTransform:
             >>> indexes = transform.get_indexes()
             >>> print(indexes)  # [3, 18, 7, 2]
         """
-        raise NotImplementedError
+        return random.randint(0, len(self.dataset) - 1)
 
     @staticmethod
     def _update_label_text(labels):
@@ -877,7 +877,6 @@ class MixUp(BaseMixTransform):
         p (float): Probability of applying MixUp augmentation.
 
     Methods:
-        get_indexes: Returns a random index from the dataset.
         _mix_transform: Applies MixUp augmentation to the input labels.
 
     Examples:
@@ -906,24 +905,6 @@ class MixUp(BaseMixTransform):
         """
         super().__init__(dataset=dataset, pre_transform=pre_transform, p=p)
 
-    def get_indexes(self):
-        """
-        Get a random index from the dataset.
-
-        This method returns a single random index from the dataset, which is used to select an image for MixUp
-        augmentation.
-
-        Returns:
-            (int): A random integer index within the range of the dataset length.
-
-        Examples:
-            >>> mixup = MixUp(dataset)
-            >>> index = mixup.get_indexes()
-            >>> print(index)
-            42
-        """
-        return random.randint(0, len(self.dataset) - 1)
-
     def _mix_transform(self, labels):
         """
         Applies MixUp augmentation to the input labels.
@@ -949,6 +930,122 @@ class MixUp(BaseMixTransform):
         return labels
 
 
+class CutMix(BaseMixTransform):
+    """
+    Applies CutMix augmentation to image datasets as described in the paper https://arxiv.org/abs/1905.04899.
+
+    CutMix combines two images by replacing a random rectangular region of one image with the corresponding region from another image,
+    and adjusts the labels proportionally to the area of the mixed region.
+
+    Attributes:
+        dataset (Any): The dataset to which CutMix augmentation will be applied.
+        pre_transform (Callable | None): Optional transform to apply before CutMix.
+        p (float): Probability of applying CutMix augmentation.
+        beta (float): Beta distribution parameter for sampling the mixing ratio (default=1.0).
+        num_areas (int): Number of areas to try to cut and mix (default=3).
+
+    Methods:
+        _mix_transform: Applies CutMix augmentation to the input labels.
+        _rand_bbox: Generates random bounding box coordinates for the cut region.
+
+    Examples:
+        >>> from ultralytics.data.augment import CutMix
+        >>> dataset = YourDataset(...)  # Your image dataset
+        >>> cutmix = CutMix(dataset, p=0.5)
+        >>> augmented_labels = cutmix(original_labels)
+    """
+
+    def __init__(self, dataset, pre_transform=None, p=0.0, beta=1.0, num_areas=3) -> None:
+        """
+        Initializes the CutMix augmentation object.
+
+        Args:
+            dataset (Any): The dataset to which CutMix augmentation will be applied.
+            pre_transform (Callable | None): Optional transform to apply before CutMix.
+            p (float): Probability of applying CutMix augmentation.
+            beta (float): Beta distribution parameter for sampling the mixing ratio (default=1.0).
+            num_areas (int): Number of areas to try to cut and mix (default=3).
+        """
+        super().__init__(dataset=dataset, pre_transform=pre_transform, p=p)
+        self.beta = beta
+        self.num_areas = num_areas
+
+    def _rand_bbox(self, width, height):
+        """
+        Generates random bounding box coordinates for the cut region.
+
+        Args:
+            width (int): Width of the image.
+            height (int): Height of the image.
+
+        Returns:
+            (tuple): (x1, y1, x2, y2) coordinates of the bounding box.
+        """
+        # Sample mixing ratio from Beta distribution
+        lam = np.random.beta(self.beta, self.beta)
+
+        cut_ratio = np.sqrt(1.0 - lam)
+        cut_w = int(width * cut_ratio)
+        cut_h = int(height * cut_ratio)
+
+        # Random center
+        cx = np.random.randint(width)
+        cy = np.random.randint(height)
+
+        # Bounding box coordinates
+        x1 = np.clip(cx - cut_w // 2, 0, width)
+        y1 = np.clip(cy - cut_h // 2, 0, height)
+        x2 = np.clip(cx + cut_w // 2, 0, width)
+        y2 = np.clip(cy + cut_h // 2, 0, height)
+
+        return x1, y1, x2, y2
+
+    def _mix_transform(self, labels):
+        """
+        Applies CutMix augmentation to the input labels.
+
+        Args:
+            labels (dict): A dictionary containing the original image and label information.
+
+        Returns:
+            (dict): A dictionary containing the mixed image and adjusted labels.
+
+        Examples:
+            >>> cutter = CutMix(dataset)
+            >>> mixed_labels = cutter._mix_transform(labels)
+        """
+        # Get a random second image
+        h, w = labels["img"].shape[:2]
+
+        cut_areas = np.asarray([self._rand_bbox(w, h) for _ in range(self.num_areas)], dtype=np.float32)
+        ioa1 = bbox_ioa(cut_areas, labels["instances"].bboxes)  # (self.num_areas, num_boxes)
+        idx = np.nonzero(ioa1.sum(axis=1) <= 0)[0]
+        if len(idx) == 0:
+            return labels
+
+        labels2 = labels.pop("mix_labels")[0]
+        area = cut_areas[np.random.choice(idx)]  # randomle select one
+        ioa2 = bbox_ioa(area[None], labels2["instances"].bboxes).squeeze(0)
+        indexes2 = np.nonzero(ioa2 >= 0.01 if len(labels["instances"].segments) else 0.1)[0]
+
+        instances2 = labels2["instances"][indexes2]
+        instances2.convert_bbox("xyxy")
+        instances2.denormalize(w, h)
+
+        # Apply CutMix
+        x1, y1, x2, y2 = area.astype(np.int32)
+        labels["img"][y1:y2, x1:x2] = labels2["img"][y1:y2, x1:x2]
+
+        # Restrain instances2 to the random bounding border
+        instances2.add_padding(-x1, -y1)
+        instances2.clip(x2 - x1, y2 - y1)
+        instances2.add_padding(x1, y1)
+
+        labels["cls"] = np.concatenate([labels["cls"], labels2["cls"][indexes2]], axis=0)
+        labels["instances"] = Instances.concatenate([labels["instances"], instances2], axis=0)
+        return labels
+
+
 class RandomPerspective:
     """
     Implements random perspective and affine transformations on images and corresponding annotations.
@@ -1655,7 +1752,6 @@ class CopyPaste(BaseMixTransform):
         p (float): Probability of applying Copy-Paste augmentation.
 
     Methods:
-        get_indexes: Returns a random index from the dataset.
         _mix_transform: Applies Copy-Paste augmentation to the input labels.
         __call__: Applies the Copy-Paste transformation to images and annotations.
 
@@ -1672,10 +1768,6 @@ class CopyPaste(BaseMixTransform):
         assert mode in {"flip", "mixup"}, f"Expected `mode` to be `flip` or `mixup`, but got {mode}."
         self.mode = mode
 
-    def get_indexes(self):
-        """Returns a list of random indexes from the dataset for CopyPaste augmentation."""
-        return random.randint(0, len(self.dataset) - 1)
-
     def _mix_transform(self, labels):
         """Applies Copy-Paste augmentation to combine objects from another image into the current image."""
         labels2 = labels["mix_labels"][0]
@@ -2445,6 +2537,7 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
         [
             pre_transform,
             MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup),
+            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),

ultralytics/data/dataset.py

@@ -215,6 +215,7 @@ class YOLODataset(BaseDataset):
         if self.augment:
             hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
             hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
+            hyp.cutmix = hyp.cutmix if self.augment and not self.rect else 0.0
             transforms = v8_transforms(self, self.imgsz, hyp)
         else:
             transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
@@ -235,14 +236,15 @@ class YOLODataset(BaseDataset):
 
     def close_mosaic(self, hyp):
         """
-        Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations.
+        Disable mosaic, copy_paste, mixup and cutmix augmentations by setting their probabilities to 0.0.
 
         Args:
             hyp (dict): Hyperparameters for transforms.
         """
-        hyp.mosaic = 0.0  # set mosaic ratio=0.0
-        hyp.copy_paste = 0.0  # keep the same behavior as previous v8 close-mosaic
-        hyp.mixup = 0.0  # keep the same behavior as previous v8 close-mosaic
+        hyp.mosaic = 0.0
+        hyp.copy_paste = 0.0
+        hyp.mixup = 0.0
+        hyp.cutmix = 0.0
         self.transforms = self.build_transforms(hyp)
 
     def update_labels_info(self, label):
@@ -441,7 +443,7 @@ class GroundingDataset(YOLODataset):
         """
         assert task in {"detect", "segment"}, "GroundingDataset currently only supports `detect` and `segment` tasks"
         self.json_file = json_file
-        super().__init__(*args, task=task, data={}, **kwargs)
+        super().__init__(*args, task=task, data={"channels": 3}, **kwargs)
 
     def get_img_files(self, img_path):
         """

ultralytics/engine/exporter.py

@@ -95,7 +95,6 @@ from ultralytics.utils import (
     yaml_save,
 )
 from ultralytics.utils.checks import (
-    IS_PYTHON_MINIMUM_3_12,
     check_imgsz,
     check_is_path_safe,
     check_requirements,
@@ -549,7 +548,7 @@ class Exporter:
         """YOLO ONNX export."""
         requirements = ["onnx>=1.12.0"]
         if self.args.simplify:
-            requirements += ["onnxslim", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
+            requirements += ["onnxslim>=0.1.46", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
         check_requirements(requirements)
         import onnx  # noqa
 
@@ -569,12 +568,6 @@ class Exporter:
                 dynamic["output0"].pop(2)
         if self.args.nms and self.model.task == "obb":
             self.args.opset = opset_version  # for NMSModel
-            # OBB error https://github.com/pytorch/pytorch/issues/110859#issuecomment-1757841865
-            try:
-                torch.onnx.register_custom_op_symbolic("aten::lift_fresh", lambda g, x: x, opset_version)
-            except RuntimeError:  # it will fail if it's already registered
-                pass
-            check_requirements("onnxslim>=0.1.46")  # Older versions has bug with OBB
 
         with arange_patch(self.args):
             export_onnx(
@@ -650,7 +643,7 @@ class Exporter:
                 """Quantization transform function."""
                 data_item: torch.Tensor = data_item["img"] if isinstance(data_item, dict) else data_item
                 assert data_item.dtype == torch.uint8, "Input image must be uint8 for the quantization preprocessing"
-                im = data_item.numpy().astype(np.float32) / 255.0  # uint8 to fp16/32 and 0 - 255 to 0.0 - 1.0
+                im = data_item.numpy().astype(np.float32) / 255.0  # uint8 to fp16/32 and 0-255 to 0.0-1.0
                 return np.expand_dims(im, 0) if im.ndim == 3 else im
 
             # Generate calibration data for integer quantization
@@ -914,14 +907,13 @@ class Exporter:
             import tensorflow as tf  # noqa
         check_requirements(
             (
-                "keras",  # required by 'onnx2tf' package
                 "tf_keras",  # required by 'onnx2tf' package
                 "sng4onnx>=1.0.1",  # required by 'onnx2tf' package
                 "onnx_graphsurgeon>=0.3.26",  # required by 'onnx2tf' package
                 "ai-edge-litert>=1.2.0",  # required by 'onnx2tf' package
                 "onnx>=1.12.0",
                 "onnx2tf>=1.26.3",
-                "onnxslim>=0.1.31",
+                "onnxslim>=0.1.46",
                 "onnxruntime-gpu" if cuda else "onnxruntime",
                 "protobuf>=5",
             ),
@@ -1027,8 +1019,6 @@ class Exporter:
     @try_export
     def export_edgetpu(self, tflite_model="", prefix=colorstr("Edge TPU:")):
         """YOLO Edge TPU export https://coral.ai/docs/edgetpu/models-intro/."""
-        LOGGER.warning(f"{prefix} Edge TPU known bug https://github.com/ultralytics/ultralytics/issues/1185")
-
         cmd = "edgetpu_compiler --version"
         help_url = "https://coral.ai/docs/edgetpu/compiler/"
         assert LINUX, f"export only supported on Linux. See {help_url}"
@@ -1126,7 +1116,8 @@ class Exporter:
         """YOLO IMX export."""
         gptq = False
         assert LINUX, (
-            "export only supported on Linux. See https://developer.aitrios.sony-semicon.com/en/raspberrypi-ai-camera/documentation/imx500-converter"
+            "export only supported on Linux. "
+            "See https://developer.aitrios.sony-semicon.com/en/raspberrypi-ai-camera/documentation/imx500-converter"
         )
         if getattr(self.model, "end2end", False):
             raise ValueError("IMX export is not supported for end2end models.")
@@ -1274,81 +1265,12 @@ class Exporter:
 
         return f, None
 
-    def _add_tflite_metadata(self, file, use_flatbuffers=False):
+    def _add_tflite_metadata(self, file):
         """Add metadata to *.tflite models per https://ai.google.dev/edge/litert/models/metadata."""
-        if not use_flatbuffers:
-            import zipfile
-
-            with zipfile.ZipFile(file, "a", zipfile.ZIP_DEFLATED) as zf:
-                zf.writestr("metadata.json", json.dumps(self.metadata, indent=2))
-            return
+        import zipfile
 
-        if IS_PYTHON_MINIMUM_3_12:
-            LOGGER.warning(f"TFLite Support package may not be compatible with Python>=3.12 environments for {file}")
-
-        # Update old 'flatbuffers' included inside tensorflow package
-        check_requirements(("tflite_support", "flatbuffers>=23.5.26,<100; platform_machine == 'aarch64'"))
-        import flatbuffers
-
-        try:
-            # TFLite Support bug https://github.com/tensorflow/tflite-support/issues/954#issuecomment-2108570845
-            from tensorflow_lite_support.metadata import metadata_schema_py_generated as schema  # noqa
-            from tensorflow_lite_support.metadata.python import metadata  # noqa
-        except ImportError:  # ARM64 systems may not have the 'tensorflow_lite_support' package available
-            from tflite_support import metadata  # noqa
-            from tflite_support import metadata_schema_py_generated as schema  # noqa
-
-        # Create model info
-        model_meta = schema.ModelMetadataT()
-        model_meta.name = self.metadata["description"]
-        model_meta.version = self.metadata["version"]
-        model_meta.author = self.metadata["author"]
-        model_meta.license = self.metadata["license"]
-
-        # Label file
-        tmp_file = Path(file).parent / "temp_meta.txt"
-        with open(tmp_file, "w", encoding="utf-8") as f:
-            f.write(str(self.metadata))
-
-        label_file = schema.AssociatedFileT()
-        label_file.name = tmp_file.name
-        label_file.type = schema.AssociatedFileType.TENSOR_AXIS_LABELS
-
-        # Create input info
-        input_meta = schema.TensorMetadataT()
-        input_meta.name = "image"
-        input_meta.description = "Input image to be detected."
-        input_meta.content = schema.ContentT()
-        input_meta.content.contentProperties = schema.ImagePropertiesT()
-        input_meta.content.contentProperties.colorSpace = schema.ColorSpaceType.RGB
-        input_meta.content.contentPropertiesType = schema.ContentProperties.ImageProperties
-
-        # Create output info
-        output1 = schema.TensorMetadataT()
-        output1.name = "output"
-        output1.description = "Coordinates of detected objects, class labels, and confidence score"
-        output1.associatedFiles = [label_file]
-        if self.model.task == "segment":
-            output2 = schema.TensorMetadataT()
-            output2.name = "output"
-            output2.description = "Mask protos"
-            output2.associatedFiles = [label_file]
-
-        # Create subgraph info
-        subgraph = schema.SubGraphMetadataT()
-        subgraph.inputTensorMetadata = [input_meta]
-        subgraph.outputTensorMetadata = [output1, output2] if self.model.task == "segment" else [output1]
-        model_meta.subgraphMetadata = [subgraph]
-
-        b = flatbuffers.Builder(0)
-        b.Finish(model_meta.Pack(b), metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
-        metadata_buf = b.Output()
-
-        populator = metadata.MetadataPopulator.with_model_file(str(file))
-        populator.load_metadata_buffer(metadata_buf)
-        populator.load_associated_files([str(tmp_file)])
-        populator.populate()
-        tmp_file.unlink()
+        with zipfile.ZipFile(file, "a", zipfile.ZIP_DEFLATED) as zf:
+            zf.writestr("metadata.json", json.dumps(self.metadata, indent=2))
 
     def _pipeline_coreml(self, model, weights_dir=None, prefix=colorstr("CoreML Pipeline:")):
         """YOLO CoreML pipeline."""

ultralytics/engine/tuner.py

@@ -88,8 +88,9 @@ class Tuner:
             "flipud": (0.0, 1.0),  # image flip up-down (probability)
             "fliplr": (0.0, 1.0),  # image flip left-right (probability)
             "bgr": (0.0, 1.0),  # image channel bgr (probability)
-            "mosaic": (0.0, 1.0),  # image mixup (probability)
+            "mosaic": (0.0, 1.0),  # image mosaic (probability)
             "mixup": (0.0, 1.0),  # image mixup (probability)
+            "cutmix": (0.0, 1.0),  # image cutmix (probability)
             "copy_paste": (0.0, 1.0),  # segment copy-paste (probability)
         }
         self.args = get_cfg(overrides=args)

ultralytics/models/rtdetr/val.py

@@ -63,6 +63,7 @@ class RTDETRDataset(YOLODataset):
         if self.augment:
             hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
             hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
+            hyp.cutmix = hyp.cutmix if self.augment and not self.rect else 0.0
             transforms = v8_transforms(self, self.imgsz, hyp, stretch=True)
         else:
             # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scale_fill=True)])

ultralytics/models/yolo/world/train_world.py

@@ -3,7 +3,7 @@
 from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_dataset
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.world import WorldTrainer
-from ultralytics.utils import DEFAULT_CFG
+from ultralytics.utils import DEFAULT_CFG, LOGGER
 from ultralytics.utils.torch_utils import de_parallel
 
 
@@ -93,14 +93,14 @@ class WorldTrainerFromScratch(WorldTrainer):
         """
         gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
         if mode != "train":
-            return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs)
-        dataset = [
-            build_yolo_dataset(self.args, im_path, batch, self.data, stride=gs, multi_modal=True)
+            return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=False, stride=gs)
+        datasets = [
+            build_yolo_dataset(self.args, im_path, batch, self.training_data[im_path], stride=gs, multi_modal=True)
             if isinstance(im_path, str)
             else build_grounding(self.args, im_path["img_path"], im_path["json_file"], batch, stride=gs)
             for im_path in img_path
         ]
-        return YOLOConcatDataset(dataset) if len(dataset) > 1 else dataset[0]
+        return YOLOConcatDataset(datasets) if len(datasets) > 1 else datasets[0]
 
     def get_dataset(self):
         """
@@ -140,8 +140,20 @@ class WorldTrainerFromScratch(WorldTrainer):
         # NOTE: to make training work properly, set `nc` and `names`
         final_data["nc"] = data["val"][0]["nc"]
         final_data["names"] = data["val"][0]["names"]
+        # NOTE: add path with lvis path
+        final_data["path"] = data["val"][0]["path"]
         final_data["channels"] = data["val"][0]["channels"]
         self.data = final_data
+        if self.args.single_cls:  # consistent with base trainer
+            LOGGER.info("Overriding class names with single class.")
+            self.data["names"] = {0: "object"}
+            self.data["nc"] = 1
+        self.training_data = {}
+        for d in data["train"]:
+            if self.args.single_cls:
+                d["names"] = {0: "object"}
+                d["nc"] = 1
+            self.training_data[d["train"]] = d
         return final_data["train"], final_data["val"][0]
 
     def plot_training_labels(self):

ultralytics/models/yolo/yoloe/__init__.py

@@ -1,7 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from .predict import YOLOEVPDetectPredictor, YOLOEVPSegPredictor
-from .train import YOLOEPEFreeTrainer, YOLOEPETrainer, YOLOETrainer, YOLOEVPTrainer
+from .train import YOLOEPEFreeTrainer, YOLOEPETrainer, YOLOETrainer, YOLOETrainerFromScratch, YOLOEVPTrainer
 from .train_seg import YOLOEPESegTrainer, YOLOESegTrainer, YOLOESegTrainerFromScratch, YOLOESegVPTrainer
 from .val import YOLOEDetectValidator, YOLOESegValidator
 
@@ -18,4 +18,5 @@ __all__ = [
     "YOLOEPEFreeTrainer",
     "YOLOEVPDetectPredictor",
     "YOLOEVPSegPredictor",
+    "YOLOETrainerFromScratch",
 ]

ultralytics/models/yolo/yoloe/train.py

@@ -6,14 +6,14 @@ from pathlib import Path
 
 import torch
 
-from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_dataset
+from ultralytics.data import YOLOConcatDataset, build_yolo_dataset
 from ultralytics.data.augment import LoadVisualPrompt
-from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.detect import DetectionTrainer, DetectionValidator
 from ultralytics.nn.tasks import YOLOEModel
 from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.torch_utils import de_parallel
 
+from ..world.train_world import WorldTrainerFromScratch
 from .val import YOLOEDetectValidator
 
 
@@ -92,11 +92,6 @@ class YOLOETrainer(DetectionTrainer):
             self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs, multi_modal=mode == "train"
         )
 
-    def preprocess_batch(self, batch):
-        """Process batch for training, moving text features to the appropriate device."""
-        batch = super().preprocess_batch(batch)
-        return batch
-
 
 class YOLOEPETrainer(DetectionTrainer):
     """Fine-tune YOLOE model in linear probing way."""
@@ -144,30 +139,9 @@ class YOLOEPETrainer(DetectionTrainer):
         return model
 
 
-class YOLOETrainerFromScratch(YOLOETrainer):
+class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
     """Train YOLOE models from scratch."""
 
-    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
-        """
-        Initialize the YOLOETrainerFromScratch class.
-
-        This class extends YOLOETrainer to train YOLOE models from scratch. It inherits all functionality from
-        the parent class while providing specialized initialization for training without pre-trained weights.
-
-        Args:
-            cfg (dict, optional): Configuration dictionary with training parameters. Defaults to DEFAULT_CFG.
-            overrides (dict, optional): Dictionary of parameter overrides for configuration.
-            _callbacks (list, optional): List of callback functions to be executed during training.
-
-        Examples:
-            >>> from ultralytics.models.yoloe.train import YOLOETrainerFromScratch
-            >>> trainer = YOLOETrainerFromScratch()
-            >>> trainer.train()
-        """
-        if overrides is None:
-            overrides = {}
-        super().__init__(cfg, overrides, _callbacks)
-
     def build_dataset(self, img_path, mode="train", batch=None):
         """
         Build YOLO Dataset for training or validation.
@@ -183,17 +157,12 @@ class YOLOETrainerFromScratch(YOLOETrainer):
         Returns:
             (YOLOConcatDataset | Dataset): The constructed dataset for training or validation.
         """
-        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
-        if mode != "train":
-            return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=False, stride=gs)
-        datasets = [
-            build_yolo_dataset(self.args, im_path, batch, self.training_data[im_path], stride=gs, multi_modal=True)
-            if isinstance(im_path, str)
-            else build_grounding(self.args, im_path["img_path"], im_path["json_file"], batch, stride=gs)
-            for im_path in img_path
-        ]
-        self.set_text_embeddings(datasets, batch)  # cache text embeddings to accelerate training
-        return YOLOConcatDataset(datasets) if len(datasets) > 1 else datasets[0]
+        datasets = WorldTrainerFromScratch.build_dataset(self, img_path, mode, batch)
+        if mode == "train":
+            self.set_text_embeddings(
+                datasets.datasets if hasattr(datasets, "datasets") else [datasets], batch
+            )  # cache text embeddings to accelerate training
+        return datasets
 
     def set_text_embeddings(self, datasets, batch):
         """
@@ -225,7 +194,7 @@ class YOLOETrainerFromScratch(YOLOETrainer):
 
     def preprocess_batch(self, batch):
         """Process batch for training, moving text features to the appropriate device."""
-        batch = super().preprocess_batch(batch)
+        batch = DetectionTrainer.preprocess_batch(self, batch)
 
         texts = list(itertools.chain(*batch["texts"]))
         txt_feats = torch.stack([self.text_embeddings[text] for text in texts]).to(self.device)
@@ -246,6 +215,7 @@ class YOLOETrainerFromScratch(YOLOETrainer):
             (dict): Dictionary mapping text samples to their embeddings.
         """
         if cache_path.exists():
+            LOGGER.info(f"Reading existed cache from '{cache_path}'")
             return torch.load(cache_path)
         assert self.model is not None
         txt_feats = self.model.get_text_pe(texts, batch, without_reprta=True)
@@ -253,77 +223,6 @@ class YOLOETrainerFromScratch(YOLOETrainer):
         torch.save(txt_map, cache_path)
         return txt_map
 
-    def get_dataset(self):
-        """
-        Get train and validation paths from data dictionary.
-
-        Processes the data configuration to extract paths for training and validation datasets,
-        handling both YOLO detection datasets and grounding datasets.
-
-        Returns:
-            (str): Train dataset path.
-            (str): Validation dataset path.
-
-        Raises:
-            AssertionError: If train or validation datasets are not found, or if validation has multiple datasets.
-        """
-        final_data = {}
-        data_yaml = self.args.data
-        assert data_yaml.get("train", False), "train dataset not found"  # object365.yaml
-        assert data_yaml.get("val", False), "validation dataset not found"  # lvis.yaml
-        data = {k: [check_det_dataset(d) for d in v.get("yolo_data", [])] for k, v in data_yaml.items()}
-        assert len(data["val"]) == 1, f"Only support validating on 1 dataset for now, but got {len(data['val'])}."
-        val_split = "minival" if "lvis" in data["val"][0]["val"] else "val"
-        for d in data["val"]:
-            if d.get("minival") is None:  # for lvis dataset
-                continue
-            d["minival"] = str(d["path"] / d["minival"])
-        for s in ["train", "val"]:
-            final_data[s] = [d["train" if s == "train" else val_split] for d in data[s]]
-            # save grounding data if there's one
-            grounding_data = data_yaml[s].get("grounding_data")
-            if grounding_data is None:
-                continue
-            grounding_data = grounding_data if isinstance(grounding_data, list) else [grounding_data]
-            for g in grounding_data:
-                assert isinstance(g, dict), f"Grounding data should be provided in dict format, but got {type(g)}"
-            final_data[s] += grounding_data
-        # NOTE: to make training work properly, set `nc` and `names`
-        final_data["nc"] = data["val"][0]["nc"]
-        final_data["names"] = data["val"][0]["names"]
-        # NOTE: add path with lvis path
-        final_data["path"] = data["val"][0]["path"]
-        self.data = final_data
-        if self.args.single_cls:  # consistent with base trainer
-            LOGGER.info("Overriding class names with single class.")
-            self.data["names"] = {0: "object"}
-            self.data["nc"] = 1
-        self.training_data = {}
-        for d in data["train"]:
-            if self.args.single_cls:
-                d["names"] = {0: "object"}
-                d["nc"] = 1
-            self.training_data[d["train"]] = d
-        return final_data["train"], final_data["val"][0]
-
-    def plot_training_labels(self):
-        """Do not plot labels for YOLO-World training."""
-        pass
-
-    def final_eval(self):
-        """
-        Perform final evaluation on the validation dataset.
-
-        Configures the validator with the appropriate dataset and split before running evaluation.
-
-        Returns:
-            (dict): Evaluation metrics.
-        """
-        val = self.args.data["val"]["yolo_data"][0]
-        self.validator.args.data = val
-        self.validator.args.split = "minival" if isinstance(val, str) and "lvis" in val else "val"
-        return super().final_eval()
-
 
 class YOLOEPEFreeTrainer(YOLOEPETrainer, YOLOETrainerFromScratch):
     """Train prompt-free YOLOE model."""
@@ -337,7 +236,7 @@ class YOLOEPEFreeTrainer(YOLOEPETrainer, YOLOETrainerFromScratch):
 
     def preprocess_batch(self, batch):
         """Preprocesses a batch of images for YOLOE training, adjusting formatting and dimensions as needed."""
-        batch = super(YOLOETrainer, self).preprocess_batch(batch)
+        batch = DetectionTrainer.preprocess_batch(self, batch)
         return batch
 
     def set_text_embeddings(self, datasets, batch):

ultralytics/models/yolo/yoloe/train_seg.py

@@ -5,7 +5,7 @@ from copy import copy, deepcopy
 
 from ultralytics.models.yolo.segment import SegmentationTrainer
 from ultralytics.nn.tasks import YOLOESegModel
-from ultralytics.utils import DEFAULT_CFG, RANK
+from ultralytics.utils import RANK
 
 from .train import YOLOETrainer, YOLOETrainerFromScratch, YOLOEVPTrainer
 from .val import YOLOESegValidator
@@ -24,22 +24,6 @@ class YOLOESegTrainer(YOLOETrainer, SegmentationTrainer):
         _callbacks (list): List of callback functions for training events.
     """
 
-    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
-        """
-        Initialize the YOLOESegTrainer class.
-
-        This class combines YOLOETrainer and SegmentationTrainer to provide training functionality
-        specifically for YOLOE segmentation models.
-
-        Args:
-            cfg (Dict): Configuration dictionary with training parameters.
-            overrides (Dict, optional): Dictionary with parameter overrides.
-            _callbacks (List, optional): List of callback functions for training events.
-        """
-        if overrides is None:
-            overrides = {}
-        super().__init__(cfg, overrides, _callbacks)
-
     def get_model(self, cfg=None, weights=None, verbose=True):
         """
         Return YOLOESegModel initialized with specified config and weights.

ultralytics/trackers/bot_sort.py

@@ -17,7 +17,7 @@ from .utils.kalman_filter import KalmanFilterXYWH
 
 class BOTrack(STrack):
     """
-    An extended version of the STrack class for YOLOv8, adding object tracking features.
+    An extended version of the STrack class for YOLO, adding object tracking features.
 
     This class extends the STrack class to include additional functionalities for object tracking, such as feature
     smoothing, Kalman filter prediction, and reactivation of tracks.
@@ -150,7 +150,7 @@ class BOTrack(STrack):
 
 class BOTSORT(BYTETracker):
     """
-    An extended version of the BYTETracker class for YOLOv8, designed for object tracking with ReID and GMC algorithm.
+    An extended version of the BYTETracker class for YOLO, designed for object tracking with ReID and GMC algorithm.
 
     Attributes:
         proximity_thresh (float): Threshold for spatial proximity (IoU) between tracks and detections.
@@ -163,7 +163,7 @@ class BOTSORT(BYTETracker):
         get_kalmanfilter: Return an instance of KalmanFilterXYWH for object tracking.
         init_track: Initialize track with detections, scores, and classes.
         get_dists: Get distances between tracks and detections using IoU and (optionally) ReID.
-        multi_predict: Predict and track multiple objects with YOLOv8 model.
+        multi_predict: Predict and track multiple objects with a YOLO model.
         reset: Reset the BOTSORT tracker to its initial state.
 
     Examples:
@@ -173,7 +173,7 @@ class BOTSORT(BYTETracker):
         >>> bot_sort.multi_predict(tracks)
 
     Note:
-        The class is designed to work with the YOLOv8 object detection model and supports ReID only if enabled via args.
+        The class is designed to work with a YOLO object detection model and supports ReID only if enabled via args.
     """
 
     def __init__(self, args, frame_rate=30):
@@ -197,7 +197,7 @@ class BOTSORT(BYTETracker):
         self.appearance_thresh = args.appearance_thresh
         self.encoder = (
             (lambda feats, s: [f.cpu().numpy() for f in feats])  # native features do not require any model
-            if self.args.model == "auto"
+            if args.with_reid and self.args.model == "auto"
             else ReID(args.model)
             if args.with_reid
             else None

ultralytics/utils/loss.py

@@ -794,15 +794,16 @@ class TVPSegmentLoss(TVPDetectLoss):
 
     def __init__(self, model):
         """Initialize TVPSegmentLoss with task-prompt and visual-prompt criteria using the provided model."""
+        super().__init__(model)
         self.vp_criterion = v8SegmentationLoss(model)
 
     def __call__(self, preds, batch):
         """Calculate the loss for text-visual prompt segmentation."""
         feats, pred_masks, proto = preds if len(preds) == 3 else preds[1]
-        assert self.tp_criterion.reg_max == self.vp_criterion.reg_max
+        assert self.ori_reg_max == self.vp_criterion.reg_max  # TODO: remove it
 
-        if self.tp_criterion.reg_max * 4 + self.tp_criterion.nc == feats[0].shape[1]:
-            loss = torch.zeros(4, device=self.tp_criterion.device, requires_grad=True)
+        if self.ori_reg_max * 4 + self.ori_nc == feats[0].shape[1]:
+            loss = torch.zeros(4, device=self.vp_criterion.device, requires_grad=True)
             return loss, loss.detach()
 
         vp_feats = self._get_vp_features(feats)

ultralytics/utils/ops.py

@@ -213,7 +213,7 @@ def non_max_suppression(
         multi_label (bool): If True, each box may have multiple labels.
         labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner
             list contains the apriori labels for a given image. The list should be in the format
-            output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2).
+            output by a dataloader, with each label being a tuple of (class_index, x, y, w, h).
         max_det (int): The maximum number of boxes to keep after NMS.
         nc (int): The number of classes output by the model. Any indices after this will be considered masks.
         max_time_img (float): The maximum time (seconds) for processing one image.

ultralytics/utils/tuner.py

@@ -77,8 +77,9 @@ def run_ray_tune(
         "flipud": tune.uniform(0.0, 1.0),  # image flip up-down (probability)
         "fliplr": tune.uniform(0.0, 1.0),  # image flip left-right (probability)
         "bgr": tune.uniform(0.0, 1.0),  # image channel BGR (probability)
-        "mosaic": tune.uniform(0.0, 1.0),  # image mixup (probability)
+        "mosaic": tune.uniform(0.0, 1.0),  # image mosaic (probability)
         "mixup": tune.uniform(0.0, 1.0),  # image mixup (probability)
+        "cutmix": tune.uniform(0.0, 1.0),  # image cutmix (probability)
         "copy_paste": tune.uniform(0.0, 1.0),  # segment copy-paste (probability)
     }
 

{ultralytics-8.3.118.dist-info → ultralytics-8.3.120.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.118
+Version: 8.3.120
 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>
@@ -32,7 +32,7 @@ Classifier: Operating System :: Microsoft :: Windows
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<=2.1.1,>=1.23.0
+Requires-Dist: numpy>=1.23.0
 Requires-Dist: matplotlib>=3.3.0
 Requires-Dist: opencv-python>=4.6.0
 Requires-Dist: pillow>=7.1.2
@@ -61,20 +61,19 @@ Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"
 Provides-Extra: export
 Requires-Dist: onnx>=1.12.0; extra == "export"
 Requires-Dist: coremltools>=8.0; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
-Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.12") and extra == "export"
+Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"
 Requires-Dist: tensorflow>=2.0.0; extra == "export"
 Requires-Dist: tensorflowjs>=2.0.0; extra == "export"
 Requires-Dist: tensorstore>=0.1.63; (platform_machine == "aarch64" and python_version >= "3.9") and extra == "export"
-Requires-Dist: keras; extra == "export"
 Requires-Dist: h5py!=3.11.0; platform_machine == "aarch64" and extra == "export"
 Provides-Extra: solutions
 Requires-Dist: shapely<2.1.0,>=2.0.0; extra == "solutions"
 Requires-Dist: streamlit<1.44.0,>=1.29.0; extra == "solutions"
 Provides-Extra: logging
-Requires-Dist: comet; extra == "logging"
-Requires-Dist: tensorboard>=2.13.0; extra == "logging"
-Requires-Dist: dvclive>=2.12.0; extra == "logging"
+Requires-Dist: wandb; extra == "logging"
+Requires-Dist: tensorboard; extra == "logging"
+Requires-Dist: mlflow; extra == "logging"
 Provides-Extra: extra
 Requires-Dist: hub-sdk>=0.0.12; extra == "extra"
 Requires-Dist: ipython; extra == "extra"

{ultralytics-8.3.118.dist-info → ultralytics-8.3.120.dist-info}/RECORD

@@ -7,11 +7,11 @@ 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_solutions.py,sha256=BIvg9zW0a_ggEmrPKgB_Y0MncveH-eYuN5KlqdJ6nHs,5726
-ultralytics/__init__.py,sha256=XXXjEpVt0joLJxWXDQxT5ayqfhL1PxsXFJDk2EE48wk,730
+ultralytics/__init__.py,sha256=s0vdAaSAbSlu_5DON0IAjl8rb6whRMR18hW9WkNVsfw,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
-ultralytics/cfg/__init__.py,sha256=qtkKD_vj_AVo4lrGJkoVSovO3qY9IgETkzaTHWDJZ-4,39665
-ultralytics/cfg/default.yaml,sha256=6Z_HIaObLT2i9dhbskEg_PU_IfJS2fcCsffxr_RfFpU,8257
+ultralytics/cfg/__init__.py,sha256=eZ7exHSsrTLY72atmmHKatJgJYLjfZDPXMWVmpZF9Qw,39683
+ultralytics/cfg/default.yaml,sha256=zSiCmQp_HRlh0gZe_AZSjNQNe1aNDoX2vcNUo5oJs2Q,8306
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=_xlEDIJ9XkUo0v_iNL7FW079BoSeZtKSuLteKTtGbA8,3275
 ultralytics/cfg/datasets/DOTAv1.5.yaml,sha256=SHND_CFkojxw5iQD5Mcgju2kCZIl0gW2ajuzv1cqoL0,1224
 ultralytics/cfg/datasets/DOTAv1.yaml,sha256=j_DvXVQzZ4dQmf8I7oPX4v9xO3WZXztxV4Xo9VhUTsM,1194
@@ -104,11 +104,11 @@ ultralytics/cfg/trackers/botsort.yaml,sha256=8fM3y4TXKKT_5aWsqmQw5JEgwNlBGlRaf8L
 ultralytics/cfg/trackers/bytetrack.yaml,sha256=6u-tiZlk16EqEwkNXaMrza6PAQmWj_ypgv26LGCtPDg,886
 ultralytics/data/__init__.py,sha256=nAXaL1puCc7z_NjzQNlJnhbVhT9Fla2u7Dsqo7q1dAc,644
 ultralytics/data/annotator.py,sha256=VEwb11FsEZm75qlEp8XDHFGKW0_rGsEaFDaBVd771Kw,2902
-ultralytics/data/augment.py,sha256=Nv0q6_oDHz0fdEPRPOAI29JTLI9KC4IeMv-YW943iLQ,125239
+ultralytics/data/augment.py,sha256=m0haieHkMrpe-nEApapfR4mEuOnCw8I4k-tvTVJpOnU,129172
 ultralytics/data/base.py,sha256=uMh_xzs6ci1hciDLpbVW2ZQr7js0o8jctE8KhL2T7Z4,19015
 ultralytics/data/build.py,sha256=FVIkgLGv5n1C7SRDrQiKOMDcI7V59WmEihKslzvEISg,9651
 ultralytics/data/converter.py,sha256=znXH2XTdo0Q4NDHMny1ydVBvrxKn2kbbwI-X5bn1MlQ,26890
-ultralytics/data/dataset.py,sha256=oVtLS1VQzgI0r9thu0W3Yqr1oHPTs8rLS2SlBIIWFxE,34820
+ultralytics/data/dataset.py,sha256=hbsjhmZBO-T1_gkUAm128kKowdwsLNwnK2lhnzmxJB8,34826
 ultralytics/data/loaders.py,sha256=o844tZlfZEhXop16t-hwaEQHhbfP3_bQMS0whF_NSos,28531
 ultralytics/data/split.py,sha256=6LHB1z8woXurWjXfM-Zm2thRr1KXvzR18CFJA-SDUvE,4677
 ultralytics/data/split_dota.py,sha256=p8eVGht9tABSVbf9vwvxA_AQYEva3IGHePKlMeNrn64,11872
@@ -118,12 +118,12 @@ 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=edGxFbYCTkxuw5tbpZLmuRwn2VXEuHkOy0jq_KELJ8I,73606
+ultralytics/engine/exporter.py,sha256=d-L46TSA2U36k6LowP1t1DJqXWndsvNVxXR54a70V8Y,69771
 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/trainer.py,sha256=fdB8H6brnnQAL-ZFP6nmNmKMze0_qy0OT3jJg1B5uhQ,38864
-ultralytics/engine/tuner.py,sha256=oyjnbAExddGTBN-sm7tXFtxSgjZOZ5M81EIJSzpmqno,12581
+ultralytics/engine/tuner.py,sha256=IyFKsh4Q4a1DsjfK02DdN9cufAiBDhdhIq7F7ddguys,12646
 ultralytics/engine/validator.py,sha256=jfV81wuFDgrVVXEcPzgOpxAPrAZn-1LgpKwu9l_1-ts,17050
 ultralytics/hub/__init__.py,sha256=wDtAUKdfqob95tfFHgDJFXcsNSDSdoIQkJTm-CfIUTI,6616
 ultralytics/hub/auth.py,sha256=_bGQVLTgP-ina4fQxq2M7qkj9zKKfxb99_VWgN3S_4k,5549
@@ -144,7 +144,7 @@ ultralytics/models/rtdetr/__init__.py,sha256=_jEHmOjI_QP_nT3XJXLgYHQ6bXG4EL8Gnvn
 ultralytics/models/rtdetr/model.py,sha256=zx9UKpReYCRL7Is2DXIX9ZcJE25KE_fPZ-NYx5vF6E4,2119
 ultralytics/models/rtdetr/predict.py,sha256=5VNvyULxegg_NfGo7ugfIKHrtKhpaspJZdagU1haQmo,3942
 ultralytics/models/rtdetr/train.py,sha256=-c0DZNRscWXRNHddwHHY_OH5nLUb4LLoLyn2yIohGTg,3395
-ultralytics/models/rtdetr/val.py,sha256=MfX3drVsGOqbK0au-ZroDNfeYXmFCSembfElFmuFGuI,7301
+ultralytics/models/rtdetr/val.py,sha256=4KsGuWOsik7JXpU8mUY6ts7_wWuPvcNSxiAGIiGSuxA,7380
 ultralytics/models/sam/__init__.py,sha256=iR7B06rAEni21eptg8n4rLOP0Z_qV9y9PL-L93n4_7s,266
 ultralytics/models/sam/amg.py,sha256=r_duG0DCeCyTYfhcVh-ti10FPMl4VGL4SKc8yvbQpNU,11050
 ultralytics/models/sam/build.py,sha256=Vhml3zBGDcRO-efauNdM0ZlKTV10ADAj_aT823lPJv8,12515
@@ -186,11 +186,11 @@ ultralytics/models/yolo/segment/train.py,sha256=EIyIAjYp127Mb-DomyjPORaONu57OY_g
 ultralytics/models/yolo/segment/val.py,sha256=cXJM1JNuzDraU0SJQRIdzNxabd0bfcxiRE8wozHZChY,18415
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
 ultralytics/models/yolo/world/train.py,sha256=HUJ0XiJIGx_FA9kqNYnSFsaKWMiZUDxgkpfGoBH6UNc,4896
-ultralytics/models/yolo/world/train_world.py,sha256=E3YQVbiwzmB5Al4XX7c95nx_VBW94uqzxd96vtdIFps,7741
-ultralytics/models/yolo/yoloe/__init__.py,sha256=Z9QEmbDYABkx15zFILDsFNNz1IyZ5hl9zghaF0A5qJo,704
+ultralytics/models/yolo/world/train_world.py,sha256=-o_-85zoczEvXZHWHJaVhXQ_hAIGTFtPlgSWJmUf5AU,8287
+ultralytics/models/yolo/yoloe/__init__.py,sha256=6SLytdJtwu37qewf7CobG7C7Wl1m-xtNdvCXEasfPDE,760
 ultralytics/models/yolo/yoloe/predict.py,sha256=pjvQ8TKlAe_KIFo70qiNdOrSTITU3pcJ4VE_k7uJjDk,6994
-ultralytics/models/yolo/yoloe/train.py,sha256=JF_QxJUU3_w8yhmTfKFTpI7rVRJL1g7z7wnDikCxnn8,17691
-ultralytics/models/yolo/yoloe/train_seg.py,sha256=6nN9DbP-AJKlJ3nIlvNn8VXFwFLQEVjSOgdN5aA817M,5309
+ultralytics/models/yolo/yoloe/train.py,sha256=St3zw_XWRol9pODWU4lvKlJnWYr1lmWQNuhLFwWMge4,12989
+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
@@ -223,7 +223,7 @@ ultralytics/solutions/trackzone.py,sha256=efko4U8zT8lyNLLo9zF543rTXHefeYthxf9GV3
 ultralytics/solutions/vision_eye.py,sha256=DHf3pQzNqP71oYx3QXflvcGsg4nEYJCD1SOdSOxiWBk,2965
 ultralytics/trackers/__init__.py,sha256=Zlu_Ig5osn7hqch_g5Be_e4pwZUkeeTQiesJCi0pFGI,255
 ultralytics/trackers/basetrack.py,sha256=LYvWB5d7Woyrz_RlxaopjV07RQKH3sff_lZJfMcMxcA,4450
-ultralytics/trackers/bot_sort.py,sha256=vu3gtJnaVZ3O_Z-YBHypY2IxOZgMf63tucRGPgcf5Es,11296
+ultralytics/trackers/bot_sort.py,sha256=iDYLk3VAfsdCHisy4l9_JKxJw3YEBMgGdK0E6HthoXo,11307
 ultralytics/trackers/byte_tracker.py,sha256=D7JQ_6V8OUMQryxTrAr010UXMSaboQnI7T1xppzHXYg,20921
 ultralytics/trackers/track.py,sha256=mu6L9RWAW8Nq0vJanX-hTTUST-OmLq49d8VV96-J9u8,4817
 ultralytics/trackers/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
@@ -240,15 +240,15 @@ ultralytics/utils/errors.py,sha256=vY9h2evFSrHnZdHJVVrmm8Zzw4qVDLyo9DeYW5g0dFk,1
 ultralytics/utils/export.py,sha256=mTkebwilsT1jwIfTLgAQdkbrnZr9Sm96W-Vi7B1j5wQ,8817
 ultralytics/utils/files.py,sha256=0K4O1cgqRiXaDw7EQK13TqA5SME_RrvfDVQSPetNr5w,8042
 ultralytics/utils/instance.py,sha256=UOEsXR9V-bXNRk6BTonASBEgeMqvzzAk4S7VdXZJUAM,18090
-ultralytics/utils/loss.py,sha256=iIDVMX2nKRGi6oEv1mu86ewZtNphNK-KWkqWF5bDo6A,37477
+ultralytics/utils/loss.py,sha256=s9LT-zz1zc81Kak0xt1O5HQlv8z0Br-EvudklYs6A6E,37501
 ultralytics/utils/metrics.py,sha256=uv5O-2Ft8wYfTvDedFxiUqMZ6Nr2CL6I9ybGZiK3e2s,53773
-ultralytics/utils/ops.py,sha256=8VoH9Gw20DmJsK5IFRLxpq9At61ESuzD99gwu4XcJLg,34783
+ultralytics/utils/ops.py,sha256=YFwPrKlPcgEmgAWqnJVR0Ccx5NQgp5e3P-YYHwVSP0k,34779
 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/triton.py,sha256=xK9Db_ZUVDnIK1u76S2G-6ulIBsLfj9HN_YOaSrnMuU,5304
-ultralytics/utils/tuner.py,sha256=R_TVIfsTA8qxEPiqHBCZgh1rzqAAOwQ1gImw-0IR13g,6682
+ultralytics/utils/tuner.py,sha256=0Bp7l5dWZe1RzdvAIa11wQoX6eoAaoNRcA-EAnpofbk,6755
 ultralytics/utils/callbacks/__init__.py,sha256=hzL63Rce6VkZhP4Lcim9LKjadixaQG86nKqPhk7IkS0,242
 ultralytics/utils/callbacks/base.py,sha256=p8YCeYDp4GLcyHWFZxC2Wxr2IXLw_MfIE5ef1fOQcWk,6848
 ultralytics/utils/callbacks/clearml.py,sha256=z-MmCALz1FcNSec8CmDiFHkRd_zTzzuPDCidq_xkUXY,5990
@@ -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-8.3.118.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.118.dist-info/METADATA,sha256=3m7C_SI_4IqhMrmf4Awpl5J-T_xCNrCMHu9R409YZlw,37260
-ultralytics-8.3.118.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-ultralytics-8.3.118.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.118.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.118.dist-info/RECORD,,
+ultralytics-8.3.120.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.120.dist-info/METADATA,sha256=mP-Pkx1G9KDrCfpRBMWAJ9MlL1o-sF7NQHVUdXH-xas,37195
+ultralytics-8.3.120.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
+ultralytics-8.3.120.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.120.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.120.dist-info/RECORD,,

{ultralytics-8.3.118.dist-info → ultralytics-8.3.120.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.1)
+Generator: setuptools (80.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any