ultralytics 8.3.195__py3-none-any.whl → 8.3.196__py3-none-any.whl

ultralytics/models/yolo/yoloe/val.py

@@ -98,13 +98,6 @@ class YOLOEDetectValidator(DetectionValidator):
         visual_pe[cls_visual_num == 0] = 0
         return visual_pe.unsqueeze(0)
 
-    def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
-        """Preprocess batch data, ensuring visuals are on the same device as images."""
-        batch = super().preprocess(batch)
-        if "visuals" in batch:
-            batch["visuals"] = batch["visuals"].to(batch["img"].device, non_blocking=True)
-        return batch
-
     def get_vpe_dataloader(self, data: dict[str, Any]) -> torch.utils.data.DataLoader:
         """
         Create a dataloader for LVIS training visual prompt samples.

ultralytics/nn/modules/head.py

@@ -13,7 +13,7 @@ from torch.nn.init import constant_, xavier_uniform_
 
 from ultralytics.utils import NOT_MACOS14
 from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, make_anchors
-from ultralytics.utils.torch_utils import fuse_conv_and_bn, smart_inference_mode
+from ultralytics.utils.torch_utils import disable_dynamo, fuse_conv_and_bn, smart_inference_mode
 
 from .block import DFL, SAVPE, BNContrastiveHead, ContrastiveHead, Proto, Residual, SwiGLUFFN
 from .conv import Conv, DWConv
@@ -149,6 +149,7 @@ class Detect(nn.Module):
         y = self.postprocess(y.permute(0, 2, 1), self.max_det, self.nc)
         return y if self.export else (y, {"one2many": x, "one2one": one2one})
 
+    @disable_dynamo
     def _inference(self, x: list[torch.Tensor]) -> torch.Tensor:
         """
         Decode predicted bounding boxes and class probabilities based on multiple-level feature maps.

ultralytics/nn/tasks.py

@@ -334,7 +334,8 @@ class BaseModel(torch.nn.Module):
         if getattr(self, "criterion", None) is None:
             self.criterion = self.init_criterion()
 
-        preds = self.forward(batch["img"]) if preds is None else preds
+        if preds is None:
+            preds = self.forward(batch["img"])
         return self.criterion(preds, batch)
 
     def init_criterion(self):
@@ -775,7 +776,8 @@ class RTDETRDetectionModel(DetectionModel):
             "gt_groups": gt_groups,
         }
 
-        preds = self.predict(img, batch=targets) if preds is None else preds
+        if preds is None:
+            preds = self.predict(img, batch=targets)
         dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta = preds if self.training else preds[1]
         if dn_meta is None:
             dn_bboxes, dn_scores = None, None

ultralytics/utils/__init__.py

@@ -857,7 +857,7 @@ def get_ubuntu_version():
 
 def get_user_config_dir(sub_dir="Ultralytics"):
     """
-    Return the appropriate config directory based on the environment operating system.
+    Return a writable config dir, preferring YOLO_CONFIG_DIR and being OS-aware.
 
     Args:
         sub_dir (str): The name of the subdirectory to create.
@@ -865,27 +865,38 @@ def get_user_config_dir(sub_dir="Ultralytics"):
     Returns:
         (Path): The path to the user config directory.
     """
-    if WINDOWS:
-        path = Path.home() / "AppData" / "Roaming" / sub_dir
-    elif MACOS:  # macOS
-        path = Path.home() / "Library" / "Application Support" / sub_dir
+    if env_dir := os.getenv("YOLO_CONFIG_DIR"):
+        p = Path(env_dir).expanduser() / sub_dir
     elif LINUX:
-        path = Path.home() / ".config" / sub_dir
+        p = Path(os.getenv("XDG_CONFIG_HOME", Path.home() / ".config")) / sub_dir
+    elif WINDOWS:
+        p = Path.home() / "AppData" / "Roaming" / sub_dir
+    elif MACOS:
+        p = Path.home() / "Library" / "Application Support" / sub_dir
     else:
         raise ValueError(f"Unsupported operating system: {platform.system()}")
 
-    # GCP and AWS lambda fix, only /tmp is writeable
-    if not is_dir_writeable(path.parent):
-        LOGGER.warning(
-            f"user config directory '{path}' is not writeable, defaulting to '/tmp' or CWD. "
-            "Alternatively you can define a YOLO_CONFIG_DIR environment variable for this path."
-        )
-        path = Path("/tmp") / sub_dir if is_dir_writeable("/tmp") else Path().cwd() / sub_dir
-
-    # Create the subdirectory if it does not exist
-    path.mkdir(parents=True, exist_ok=True)
+    if p.exists():  # already created → trust it
+        return p
+    if is_dir_writeable(p.parent):  # create if possible
+        p.mkdir(parents=True, exist_ok=True)
+        return p
+
+    # Fallbacks for Docker, GCP/AWS functions where only /tmp is writeable
+    for alt in [Path("/tmp") / sub_dir, Path.cwd() / sub_dir]:
+        if alt.exists():
+            return alt
+        if is_dir_writeable(alt.parent):
+            alt.mkdir(parents=True, exist_ok=True)
+            LOGGER.warning(
+                f"user config directory '{p}' is not writeable, using '{alt}'. Set YOLO_CONFIG_DIR to override."
+            )
+            return alt
 
-    return path
+    # Last fallback → CWD
+    p = Path.cwd() / sub_dir
+    p.mkdir(parents=True, exist_ok=True)
+    return p
 
 
 # Define constants (required below)
@@ -899,7 +910,7 @@ IS_JUPYTER = is_jupyter()
 IS_PIP_PACKAGE = is_pip_package()
 IS_RASPBERRYPI = is_raspberrypi()
 GIT = GitRepo()
-USER_CONFIG_DIR = Path(os.getenv("YOLO_CONFIG_DIR") or get_user_config_dir())  # Ultralytics settings dir
+USER_CONFIG_DIR = get_user_config_dir()  # Ultralytics settings dir
 SETTINGS_FILE = USER_CONFIG_DIR / "settings.json"
 
 
@@ -1383,7 +1394,7 @@ class SettingsManager(JSONDict):
 
 def deprecation_warn(arg, new_arg=None):
     """Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument."""
-    msg = f"'{arg}' is deprecated and will be removed in in the future."
+    msg = f"'{arg}' is deprecated and will be removed in the future."
     if new_arg is not None:
         msg += f" Use '{new_arg}' instead."
     LOGGER.warning(msg)

ultralytics/utils/callbacks/tensorboard.py

@@ -70,14 +70,14 @@ def _log_tensorboard_graph(trainer) -> None:
         # Try simple method first (YOLO)
         try:
             trainer.model.eval()  # place in .eval() mode to avoid BatchNorm statistics changes
-            WRITER.add_graph(torch.jit.trace(torch_utils.de_parallel(trainer.model), im, strict=False), [])
+            WRITER.add_graph(torch.jit.trace(torch_utils.unwrap_model(trainer.model), im, strict=False), [])
             LOGGER.info(f"{PREFIX}model graph visualization added ✅")
             return
 
         except Exception:
             # Fallback to TorchScript export steps (RTDETR)
             try:
-                model = deepcopy(torch_utils.de_parallel(trainer.model))
+                model = deepcopy(torch_utils.unwrap_model(trainer.model))
                 model.eval()
                 model = model.fuse(verbose=False)
                 for m in model.modules():

ultralytics/utils/checks.py

@@ -452,6 +452,8 @@ def check_torchvision():
     to the compatibility table based on: https://github.com/pytorch/vision#installation.
     """
     compatibility_table = {
+        "2.9": ["0.24"],
+        "2.8": ["0.23"],
         "2.7": ["0.22"],
         "2.6": ["0.21"],
         "2.5": ["0.20"],

ultralytics/utils/loss.py

@@ -11,7 +11,7 @@ import torch.nn.functional as F
 from ultralytics.utils.metrics import OKS_SIGMA
 from ultralytics.utils.ops import crop_mask, xywh2xyxy, xyxy2xywh
 from ultralytics.utils.tal import RotatedTaskAlignedAssigner, TaskAlignedAssigner, dist2bbox, dist2rbox, make_anchors
-from ultralytics.utils.torch_utils import autocast
+from ultralytics.utils.torch_utils import autocast, disable_dynamo
 
 from .metrics import bbox_iou, probiou
 from .tal import bbox2dist
@@ -215,6 +215,7 @@ class v8DetectionLoss:
         self.assigner = TaskAlignedAssigner(topk=tal_topk, num_classes=self.nc, alpha=0.5, beta=6.0)
         self.bbox_loss = BboxLoss(m.reg_max).to(device)
         self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)
+        disable_dynamo(self.__class__)  # exclude from compile
 
     def preprocess(self, targets: torch.Tensor, batch_size: int, scale_tensor: torch.Tensor) -> torch.Tensor:
         """Preprocess targets by converting to tensor format and scaling coordinates."""
@@ -260,7 +261,7 @@ class v8DetectionLoss:
 
         # Targets
         targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1)
-        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
+        targets = self.preprocess(targets, batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
         gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
         mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
 
@@ -287,9 +288,14 @@ class v8DetectionLoss:
 
         # Bbox loss
         if fg_mask.sum():
-            target_bboxes /= stride_tensor
             loss[0], loss[2] = self.bbox_loss(
-                pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
+                pred_distri,
+                pred_bboxes,
+                anchor_points,
+                target_bboxes / stride_tensor,
+                target_scores,
+                target_scores_sum,
+                fg_mask,
             )
 
         loss[0] *= self.hyp.box  # box gain
@@ -329,7 +335,7 @@ class v8SegmentationLoss(v8DetectionLoss):
         try:
             batch_idx = batch["batch_idx"].view(-1, 1)
             targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
-            targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
+            targets = self.preprocess(targets, batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
             gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
             mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
         except RuntimeError as e:
@@ -388,7 +394,7 @@ class v8SegmentationLoss(v8DetectionLoss):
         loss[2] *= self.hyp.cls  # cls gain
         loss[3] *= self.hyp.dfl  # dfl gain
 
-        return loss * batch_size, loss.detach()  # loss(box, cls, dfl)
+        return loss * batch_size, loss.detach()  # loss(box, seg, cls, dfl)
 
     @staticmethod
     def single_mask_loss(
@@ -516,7 +522,7 @@ class v8PoseLoss(v8DetectionLoss):
         batch_size = pred_scores.shape[0]
         batch_idx = batch["batch_idx"].view(-1, 1)
         targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
-        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
+        targets = self.preprocess(targets, batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
         gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
         mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
 
@@ -704,7 +710,7 @@ class v8OBBLoss(v8DetectionLoss):
             targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"].view(-1, 5)), 1)
             rw, rh = targets[:, 4] * imgsz[0].item(), targets[:, 5] * imgsz[1].item()
             targets = targets[(rw >= 2) & (rh >= 2)]  # filter rboxes of tiny size to stabilize training
-            targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
+            targets = self.preprocess(targets, batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
             gt_labels, gt_bboxes = targets.split((1, 5), 2)  # cls, xywhr
             mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
         except RuntimeError as e:

ultralytics/utils/plotting.py

@@ -1004,6 +1004,7 @@ def plot_tune_results(csv_file: str = "tune_results.csv"):
     _save_one_file(csv_file.with_name("tune_fitness.png"))
 
 
+@plt_settings()
 def feature_visualization(x, module_type: str, stage: int, n: int = 32, save_dir: Path = Path("runs/detect/exp")):
     """
     Visualize feature maps of a given model module during inference.

ultralytics/utils/torch_utils.py

@@ -429,7 +429,7 @@ def get_flops(model, imgsz=640):
         return 0.0  # if not installed return 0.0 GFLOPs
 
     try:
-        model = de_parallel(model)
+        model = unwrap_model(model)
         p = next(model.parameters())
         if not isinstance(imgsz, list):
             imgsz = [imgsz, imgsz]  # expand if int/float
@@ -460,7 +460,7 @@ def get_flops_with_torch_profiler(model, imgsz=640):
     """
     if not TORCH_2_0:  # torch profiler implemented in torch>=2.0
         return 0.0
-    model = de_parallel(model)
+    model = unwrap_model(model)
     p = next(model.parameters())
     if not isinstance(imgsz, list):
         imgsz = [imgsz, imgsz]  # expand if int/float
@@ -577,17 +577,24 @@ def is_parallel(model):
     return isinstance(model, (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel))
 
 
-def de_parallel(model):
+def unwrap_model(m: nn.Module) -> nn.Module:
     """
-    De-parallelize a model: return single-GPU model if model is of type DP or DDP.
+    Unwrap compiled and parallel models to get the base model.
 
     Args:
-        model (nn.Module): Model to de-parallelize.
+        m (nn.Module): A model that may be wrapped by torch.compile (._orig_mod) or parallel wrappers such as
+            DataParallel/DistributedDataParallel (.module).
 
     Returns:
-        (nn.Module): De-parallelized model.
+        m (nn.Module): The unwrapped base model without compile or parallel wrappers.
     """
-    return model.module if is_parallel(model) else model
+    while True:
+        if hasattr(m, "_orig_mod") and isinstance(m._orig_mod, nn.Module):
+            m = m._orig_mod
+        elif hasattr(m, "module") and isinstance(m.module, nn.Module):
+            m = m.module
+        else:
+            return m
 
 
 def one_cycle(y1=0.0, y2=1.0, steps=100):
@@ -669,7 +676,7 @@ class ModelEMA:
             tau (int, optional): EMA decay time constant.
             updates (int, optional): Initial number of updates.
         """
-        self.ema = deepcopy(de_parallel(model)).eval()  # FP32 EMA
+        self.ema = deepcopy(unwrap_model(model)).eval()  # FP32 EMA
         self.updates = updates  # number of EMA updates
         self.decay = lambda x: decay * (1 - math.exp(-x / tau))  # decay exponential ramp (to help early epochs)
         for p in self.ema.parameters():
@@ -687,7 +694,7 @@ class ModelEMA:
             self.updates += 1
             d = self.decay(self.updates)
 
-            msd = de_parallel(model).state_dict()  # model state_dict
+            msd = unwrap_model(model).state_dict()  # model state_dict
             for k, v in self.ema.state_dict().items():
                 if v.dtype.is_floating_point:  # true for FP16 and FP32
                     v *= d
@@ -997,3 +1004,98 @@ class FXModel(nn.Module):
             x = m(x)  # run
             y.append(x)  # save output
         return x
+
+
+def disable_dynamo(func: Any) -> Any:
+    """
+    Disable torch.compile/dynamo for a callable when available.
+
+    Args:
+        func (Any): Callable object to wrap. Could be a function, method, or class.
+
+    Returns:
+        func (Any): Same callable, wrapped by torch._dynamo.disable when available, otherwise unchanged.
+
+    Examples:
+        >>> @disable_dynamo
+        ... def fn(x):
+        ...     return x + 1
+        >>> # Works even if torch._dynamo is not available
+        >>> _ = fn(1)
+    """
+    if hasattr(torch, "_dynamo"):
+        return torch._dynamo.disable(func)
+    return func
+
+
+def attempt_compile(
+    model: torch.nn.Module,
+    device: torch.device,
+    imgsz: int = 640,
+    use_autocast: bool = False,
+    warmup: bool = False,
+    prefix: str = colorstr("compile:"),
+) -> torch.nn.Module:
+    """
+    Compile a model with torch.compile and optionally warm up the graph to reduce first-iteration latency.
+
+    This utility attempts to compile the provided model using the inductor backend with dynamic shapes enabled and an
+    autotuning mode. If compilation is unavailable or fails, the original model is returned unchanged. An optional
+    warmup performs a single forward pass on a dummy input to prime the compiled graph and measure compile/warmup time.
+
+    Args:
+        model (torch.nn.Module): Model to compile.
+        device (torch.device): Inference device used for warmup and autocast decisions.
+        imgsz (int, optional): Square input size to create a dummy tensor with shape (1, 3, imgsz, imgsz) for warmup.
+        use_autocast (bool, optional): Whether to run warmup under autocast on CUDA or MPS devices.
+        warmup (bool, optional): Whether to execute a single dummy forward pass to warm up the compiled model.
+        prefix (str, optional): Message prefix for logger output.
+
+    Returns:
+        model (torch.nn.Module): Compiled model if compilation succeeds, otherwise the original unmodified model.
+
+    Notes:
+        - If the current PyTorch build does not provide torch.compile, the function returns the input model immediately.
+        - Warmup runs under torch.inference_mode and may use torch.autocast for CUDA/MPS to align compute precision.
+        - CUDA devices are synchronized after warmup to account for asynchronous kernel execution.
+
+    Examples:
+        >>> device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+        >>> # Try to compile and warm up a model with a 640x640 input
+        >>> model = attempt_compile(model, device=device, imgsz=640, use_autocast=True, warmup=True)
+    """
+    if not hasattr(torch, "compile"):
+        return model
+
+    LOGGER.info(f"{prefix} starting torch.compile...")
+    t0 = time.perf_counter()
+    try:
+        model = torch.compile(model, mode="max-autotune", backend="inductor")
+    except Exception as e:
+        LOGGER.warning(f"{prefix} torch.compile failed, continuing uncompiled: {e}")
+        return model
+    t_compile = time.perf_counter() - t0
+
+    t_warm = 0.0
+    if warmup:
+        # Use a single dummy tensor to build the graph shape state and reduce first-iteration latency
+        dummy = torch.zeros(1, 3, imgsz, imgsz, device=device)
+        if use_autocast and device.type == "cuda":
+            dummy = dummy.half()
+        t1 = time.perf_counter()
+        with torch.inference_mode():
+            if use_autocast and device.type in {"cuda", "mps"}:
+                with torch.autocast(device.type):
+                    _ = model(dummy)
+            else:
+                _ = model(dummy)
+        if device.type == "cuda":
+            torch.cuda.synchronize(device)
+        t_warm = time.perf_counter() - t1
+
+    total = t_compile + t_warm
+    if warmup:
+        LOGGER.info(f"{prefix} complete in {total:.1f}s (compile {t_compile:.1f}s + warmup {t_warm:.1f}s)")
+    else:
+        LOGGER.info(f"{prefix} compile complete in {t_compile:.1f}s (no warmup)")
+    return model

{ultralytics-8.3.195.dist-info → ultralytics-8.3.196.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.195
+Version: 8.3.196
 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-8.3.195.dist-info → ultralytics-8.3.196.dist-info}/RECORD

@@ -7,12 +7,12 @@ tests/test_exports.py,sha256=dWuroSyqXnrc0lE-RNTf7pZoXXXEkOs31u7nhOiEHS0,10994
 tests/test_integrations.py,sha256=kl_AKmE_Qs1GB0_91iVwbzNxofm_hFTt0zzU6JF-pg4,6323
 tests/test_python.py,sha256=2V23f2-JQsO-K4p1kj0IkCRxHykGwgd0edKJzRsBgdI,27911
 tests/test_solutions.py,sha256=6wJ9-lhyWSAm7zaR4D9L_DrUA3iJU1NgqmbQO6PIuvo,13211
-ultralytics/__init__.py,sha256=sx80eyCXBZDlBTb_btxCtaotNjo9Cvl-UrsPQFxMcUg,730
+ultralytics/__init__.py,sha256=APj9NfEx0ZIorMTCYwzpAWb-sLPKJBI99dE1cPUC-ms,730
 ultralytics/py.typed,sha256=la67KBlbjXN-_-DfGNcdOcjYumVpKG_Tkw-8n5dnGB4,8
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
-ultralytics/cfg/__init__.py,sha256=xX7qUxdcDgcjCKoQFEVQgzrwZodeKTF88CTKZe05d0Y,39955
-ultralytics/cfg/default.yaml,sha256=1SspGAK_K_DT7DBfEScJh4jsJUTOxahehZYj92xmj7o,8347
+ultralytics/cfg/__init__.py,sha256=oR-uubaBOEIetwoKr9C9WeXP7fLwVygDE_Cppoe2ho0,39974
+ultralytics/cfg/default.yaml,sha256=jnt-5OmGalqd_SSEa1cf4HkBaJy0IswpoW5gdkoF5Vc,8429
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=J4ItoUlE_EiYTmp1DFKYHfbqHkj8j4wUtRJQhaMIlBM,3275
 ultralytics/cfg/datasets/DOTAv1.5.yaml,sha256=VZ_KKFX0H2YvlFVJ8JHcLWYBZ2xiQ6Z-ROSTiKWpS7c,1211
 ultralytics/cfg/datasets/DOTAv1.yaml,sha256=JrDuYcQ0JU9lJlCA-dCkMNko_jaj6MAVGHjsfjeZ_u0,1181
@@ -106,9 +106,9 @@ ultralytics/cfg/trackers/botsort.yaml,sha256=TpRaK5kH_-QbjCQ7ekM4s_7j8I8ti3q8Hs7
 ultralytics/cfg/trackers/bytetrack.yaml,sha256=6u-tiZlk16EqEwkNXaMrza6PAQmWj_ypgv26LGCtPDg,886
 ultralytics/data/__init__.py,sha256=nAXaL1puCc7z_NjzQNlJnhbVhT9Fla2u7Dsqo7q1dAc,644
 ultralytics/data/annotator.py,sha256=f15TCDEM8SuuzHiFB8oyhTy9vfywKmPTLSPAgsZQP9I,2990
-ultralytics/data/augment.py,sha256=zyO8fjeiOlwF_xi3ATTforsV66KYzWYENFd71HC8oAA,132890
+ultralytics/data/augment.py,sha256=3ArOOP1dSnCfQRHIQ6og-XFsaLnSqrXYtx-tpbE4Kag,132893
 ultralytics/data/base.py,sha256=gWoGFifyNe1TCwtGdGp5jzKOQ9sh4b-XrfyN0PPvRaY,19661
-ultralytics/data/build.py,sha256=9Qytj451Ml7lFbGNFpslrh4Jt9EucAqL0ic_6veySnk,11511
+ultralytics/data/build.py,sha256=Bhu8E-FNSkTbz6YpNXeUBmQtN91ZtZxOCUiKYXgzV-c,11778
 ultralytics/data/converter.py,sha256=N1YFD0mG7uwL12wMcuVtF2zbISBIzTsGiy1QioDTDGs,32049
 ultralytics/data/dataset.py,sha256=AfWOLsLKjTDHRtSqODKk5OsD3ViETZTKxY4PKP2Jo5Q,36751
 ultralytics/data/loaders.py,sha256=sfQ0C86uBg9QQbN3aU0W8FIjGQmMdJTQAMK4DA1bjk8,31748
@@ -120,13 +120,13 @@ 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=c7OXFm9qBliL9zVL5g8_hVp8dVwZd3L-MnwSZDPLVrw,75428
+ultralytics/engine/exporter.py,sha256=d_2ADzklNXhVpwfAmJlp6PVuT0sLXf7O2SP486jpBy4,74966
 ultralytics/engine/model.py,sha256=1n5oqCDJYzRWPU0-79hc6txCIGpXmZVTnB-ae9nahRc,53488
-ultralytics/engine/predictor.py,sha256=PPDwvw-pVhLCefRJL7bcu4kYOCmcZBoYVHF8vfEemAo,22625
+ultralytics/engine/predictor.py,sha256=510VPYcYmEYPJmBiApQLGaFFAL4gd79rVzPCwisH7LE,22745
 ultralytics/engine/results.py,sha256=BmhePCaaTBfYrJT12t6bywZuZ_7h3tIc4IsRFuyNTdk,71499
-ultralytics/engine/trainer.py,sha256=_mTG-z6xnOdFUmB6uOF8HQkFb_uMwP0MrJHlt7X3zVw,40457
+ultralytics/engine/trainer.py,sha256=XeXZ8BAvH5ZtU7zW44Jsf7SOxtkAG8RL9NO_nhpfkZo,40898
 ultralytics/engine/tuner.py,sha256=XuqcjyGpD79pUVn-PXlJJGKXgH1yblPdYBH_R2kHWSU,20586
-ultralytics/engine/validator.py,sha256=8ky0lcMCYDY7RGYRUowDAKxEMfsPBLpT7LlgfHA-IsY,16681
+ultralytics/engine/validator.py,sha256=7tADPOXRZz0Yi7F-Z5SxcUnwytaa2MfbtuSdO8pp_l4,16966
 ultralytics/hub/__init__.py,sha256=xCF02lzlPKbdmGfO3NxLuXl5Kb0MaBZp_-fAWDHZ8zw,6698
 ultralytics/hub/auth.py,sha256=RIwZDWfW6vS2yGpZKR0xVl0-38itJYEFtmqY_M70bl8,6304
 ultralytics/hub/session.py,sha256=1o9vdd_fvPUHQ5oZgljtPePuPMUalIoXqOvE7Sdmd2o,18450
@@ -168,41 +168,41 @@ ultralytics/models/yolo/__init__.py,sha256=or0j5xvcM0usMlsFTYhNAOcQUri7reD0cD9JR
 ultralytics/models/yolo/model.py,sha256=b_F1AeBUgiSssRxZ-rGQVdB0a37rDG92h_03o0N29B8,18761
 ultralytics/models/yolo/classify/__init__.py,sha256=9--HVaNOfI1K7rn_rRqclL8FUAnpfeBrRqEQIaQw2xM,383
 ultralytics/models/yolo/classify/predict.py,sha256=o7pDE8xwjkHUUIIOph7ZVQZyGZyob24dYDQ460v_7R0,4149
-ultralytics/models/yolo/classify/train.py,sha256=DzwXQII2qf5KvSoEi03onppQpLPR1EcHowrjS5pnbVQ,10296
+ultralytics/models/yolo/classify/train.py,sha256=CXi8ZrVqYtqlzRbg3UP5kOyMYXAM4Wex8Ii0fDyv-iA,9840
 ultralytics/models/yolo/classify/val.py,sha256=6_-pbnb0skASJCqsar6_i3FyvfKNJwZ7Y8AK7wzySIU,10039
 ultralytics/models/yolo/detect/__init__.py,sha256=GIRsLYR-kT4JJx7lh4ZZAFGBZj0aebokuU0A7JbjDVA,257
 ultralytics/models/yolo/detect/predict.py,sha256=v4u3azp2zQxJKJ4L198gGIgkL7CN-6qGg1B7ypBxxbM,5390
-ultralytics/models/yolo/detect/train.py,sha256=JSEG_UDd1U3a_QqdEd1KBK228beco41O99TGBKlVH-U,9909
-ultralytics/models/yolo/detect/val.py,sha256=7lzU71_V57DG4FNcRT2f--ebLfHZcVRTsHENN9GsCAc,21324
+ultralytics/models/yolo/detect/train.py,sha256=y6qVw9az7hOMo5eXQ4a9i29wIvvwnpVfzZJJC7V7YC8,10947
+ultralytics/models/yolo/detect/val.py,sha256=OG38-x3LyCAeH3UY9jOG4axK7mfnVnTwaKpjMzQi07I,21309
 ultralytics/models/yolo/obb/__init__.py,sha256=tQmpG8wVHsajWkZdmD6cjGohJ4ki64iSXQT8JY_dydo,221
 ultralytics/models/yolo/obb/predict.py,sha256=4r1eSld6TNJlk9JG56e-DX6oPL8uBBqiuztyBpxWlHE,2888
-ultralytics/models/yolo/obb/train.py,sha256=y-9c6jNLXVx6qxE1PGVFzG1N1LYg4wFeXD94FsjJ1CE,3910
+ultralytics/models/yolo/obb/train.py,sha256=BbehrsKP0lHRV3v7rrw8wAeiDdc-szbhHAmDy0OdhoM,3461
 ultralytics/models/yolo/obb/val.py,sha256=ZNjdI5dF-igZCqJadAUb5VPTevI5i47G-bPTG8wV-CY,14171
 ultralytics/models/yolo/pose/__init__.py,sha256=63xmuHZLNzV8I76HhVXAq4f2W0KTk8Oi9eL-Y204LyQ,227
 ultralytics/models/yolo/pose/predict.py,sha256=M0C7ZfVXx4QXgv-szjnaXYEPas76ZLGAgDNNh1GG0vI,3743
-ultralytics/models/yolo/pose/train.py,sha256=MXYh-Fw7fcp3dPqKAdjcorUACIj-vfaNXqHt9GToSKY,5450
-ultralytics/models/yolo/pose/val.py,sha256=W20lg1fJzZ7nlgtBtaUhG7ftgjJ_BzjBZnShwhvNJO8,12673
+ultralytics/models/yolo/pose/train.py,sha256=laAn8ej3nihl119agEr0P8TxP8c8itI8E0I0lov4VE0,5079
+ultralytics/models/yolo/pose/val.py,sha256=U4tMWbHpCjspJ6i5DbNUav05RFCvwvfD1mjejqJIJ1c,12638
 ultralytics/models/yolo/segment/__init__.py,sha256=3IThhZ1wlkY9FvmWm9cE-5-ZyE6F1FgzAtQ6jOOFzzw,275
 ultralytics/models/yolo/segment/predict.py,sha256=zxMc1QvsQoJxm6VSbbZQ3pChvq1VbYSf7p8RX3RbPNg,5377
-ultralytics/models/yolo/segment/train.py,sha256=JfmrrKatqlbgKzbKx1rvP0juvsJn1I8OGYvctPR8Fb4,3762
-ultralytics/models/yolo/segment/val.py,sha256=mSM6e5PLeHn5PwSdrgP_7tcZ5ZoaFlIIhoykqmlVkvE,11147
+ultralytics/models/yolo/segment/train.py,sha256=MWnJ593xaEhlV0EirEMZtlz0Zj6wz6EGUFfH2dHcBIA,3324
+ultralytics/models/yolo/segment/val.py,sha256=LnRCVa1uQTmDN5qLWHpVwBL2ieF_d7ly9hSkQ7k3GwE,11112
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
-ultralytics/models/yolo/world/train.py,sha256=X0pa5D0-vTMZa24LfR1ncm1ucWqOcFitRQ0_pVtKQP0,7866
-ultralytics/models/yolo/world/train_world.py,sha256=25ZJHDYRCf2hWNYGQPlTICkFHXBTdet24XgWQ33AGh0,9551
+ultralytics/models/yolo/world/train.py,sha256=zVPtVoBedberGkth3tPuIH665HjGNJvTMLw_wLZQM84,7870
+ultralytics/models/yolo/world/train_world.py,sha256=9p9YIckrATaJjGOrpmuC8MbZX9qdoCPCEV9EGZ0sExg,9553
 ultralytics/models/yolo/yoloe/__init__.py,sha256=6SLytdJtwu37qewf7CobG7C7Wl1m-xtNdvCXEasfPDE,760
 ultralytics/models/yolo/yoloe/predict.py,sha256=pcbAUbosr1Xc436MfQi6ah3MQ6kkPzjOcltmdA3VMDE,7124
-ultralytics/models/yolo/yoloe/train.py,sha256=h11Hw-XnHfg_GPf6DrR3nMqGgQJg14rafiRZe5gVFdM,14067
+ultralytics/models/yolo/yoloe/train.py,sha256=jcXqGm8CReOCVMFLk-1bNe0Aw5PWaaQa8xBWxtrt5TY,13571
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=aCV7M8oQOvODFnU4piZdJh3tIrBJYAzZfRVRx1vRgxo,4956
-ultralytics/models/yolo/yoloe/val.py,sha256=MnS2YwhRxdqXPRlExHt-9HRp8KKIHuFdmiNH1z6LedI,9795
+ultralytics/models/yolo/yoloe/val.py,sha256=Dn6CKpfcopDVxr-WY13ATDVb_RIzQ-wsXSxxy_mpndA,9454
 ultralytics/nn/__init__.py,sha256=PJgOn2phQTTBR2P3s_JWvGeGXQpvw1znsumKow4tCuE,545
 ultralytics/nn/autobackend.py,sha256=WWHIFvCI47Wpe3NCDkoUg3esjOTJ0XGEzG3luA_uG-8,41063
-ultralytics/nn/tasks.py,sha256=9EMkmdmYLEbQVAjin2joZfqc3UfgKrrADJZKOX6Ukjw,70400
+ultralytics/nn/tasks.py,sha256=2MnuL8plr4oE_gpSIeSbCYrbkdMXdludQWWj_liWsv8,70404
 ultralytics/nn/text_model.py,sha256=pHqnKe8UueR1MuwJcIE_IvrnYIlt68QL796xjcRJs2A,15275
 ultralytics/nn/modules/__init__.py,sha256=BPMbEm1daI7Tuds3zph2_afAX7Gq1uAqK8BfiCfKTZs,3198
 ultralytics/nn/modules/activation.py,sha256=75JcIMH2Cu9GTC2Uf55r_5YLpxcrXQDaVoeGQ0hlUAU,2233
 ultralytics/nn/modules/block.py,sha256=nIIOTEuikiVWELuOt2VyfXPpvof9p4qNSdaQzq5WlCg,70618
 ultralytics/nn/modules/conv.py,sha256=U6P1ZuzQmIf09noKwp7syuWn-M98Tly2wMWOsDT3kOI,21457
-ultralytics/nn/modules/head.py,sha256=7-WuatR32jpuqR5IhwHuheAwAn_izX7e7cPOHEg7MmI,53556
+ultralytics/nn/modules/head.py,sha256=NNSrnYBDMlKssyePyK5T-WWaadfELCD_Fdn_IIbtIXs,53592
 ultralytics/nn/modules/transformer.py,sha256=l6NuuFF7j_bogcNULHBBdj5l6sf7MwiVEGz8XcRyTUM,31366
 ultralytics/nn/modules/utils.py,sha256=rn8yTObZGkQoqVzjbZWLaHiytppG4ffjMME4Lw60glM,6092
 ultralytics/solutions/__init__.py,sha256=ZoeAQavTLp8aClnhZ9tbl6lxy86GxofyGvZWTx2aWkI,1209
@@ -235,11 +235,11 @@ ultralytics/trackers/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6D
 ultralytics/trackers/utils/gmc.py,sha256=1cCmlbk5Z6Pd-rFCaiJML7o_cUm_IktMuCocTDOMGFQ,14028
 ultralytics/trackers/utils/kalman_filter.py,sha256=PPmM0lwBMdT_hGojvfLoUsBUFMBBMNRAxKbMcQa3wJ0,21619
 ultralytics/trackers/utils/matching.py,sha256=I8SX0sBaBgr4GBJ9uDGOy5LnotgNZHpB2p5RNF1sy-s,7160
-ultralytics/utils/__init__.py,sha256=8vYownbjAVDmRc2cafLetRjcq-YsUcy1LPKmSrz5yuM,53204
+ultralytics/utils/__init__.py,sha256=whSIuj-0lV0SAp4YjOeBJZ2emP1Qa8pqLnrhRiwl2Qs,53503
 ultralytics/utils/autobatch.py,sha256=i6KYLLSItKP1Q2IUlTPHrZhjcxl7UOjs0Seb8bF8pvM,5124
 ultralytics/utils/autodevice.py,sha256=d9yq6eEn05fdfzfpxeSECd0YEO61er5f7T-0kjLdofg,8843
 ultralytics/utils/benchmarks.py,sha256=lcIr--oKK0TCjUVbvrm-NtYrnszrEMuHJC9__ziM7y8,31458
-ultralytics/utils/checks.py,sha256=nKb8qnqhEZKoLPdsQ4oBcKFU9Ngw6u0pdOOjxNhy46E,34468
+ultralytics/utils/checks.py,sha256=Jw5pwREBnlyrq3zbiHEwiQXir2-f7dGpXeqY_PgoNpw,34518
 ultralytics/utils/cpu.py,sha256=OPlVxROWhQp-kEa9EkeNRKRQ-jz0KwySu5a-h91JZjk,3634
 ultralytics/utils/dist.py,sha256=g7OKPrSgjIB2wgcncSFYtFuR-uW6J0-Y1z76k4gDSz0,4170
 ultralytics/utils/downloads.py,sha256=JIlHfUg-qna5aOHRJupH7d5zob2qGZtRrs86Cp3zOJs,23029
@@ -250,14 +250,14 @@ ultralytics/utils/files.py,sha256=kxE2rkBuZL288nSN7jxLljmDnBgc16rekEXeRjhbUoo,82
 ultralytics/utils/git.py,sha256=DcaxKNQfCiG3cxdzuw7M6l_VXgaSVqkERQt_vl8UyXM,5512
 ultralytics/utils/instance.py,sha256=_b_jMTECWJGzncCiTg7FtTDSSeXGnbiAhaJhIsqbn9k,19043
 ultralytics/utils/logger.py,sha256=o_vH4CCgQat6_Sbmwm1sUAJ4muAgVcsUed-WqpGNQZw,15129
-ultralytics/utils/loss.py,sha256=sC2efov3Uwg2eT5oOzMHRfnQLZvtGXSdMuWBTKxyxPw,39816
+ultralytics/utils/loss.py,sha256=S1mzVkIPjoNUxSQjZHfTdzuMEuYvdRmwfZoMg_fMMeE,39906
 ultralytics/utils/metrics.py,sha256=xFlSqx_su96LAUpxfGP7ShEG50Qo5p5OtwR3hx4_Llc,68809
 ultralytics/utils/nms.py,sha256=pcAaKIMssVGX3jlFmEEm6P_SL9PrXsTgu0rpx-_TDi8,14199
 ultralytics/utils/ops.py,sha256=PW3fgw1d18CA2ZNQZVJqUy054cJ_9tIcxd1XnA0FPgU,26905
 ultralytics/utils/patches.py,sha256=0-2G4jXCIPnMonlft-cPcjfFcOXQS6ODwUDNUwanfg4,6541
-ultralytics/utils/plotting.py,sha256=8ze3RFly61sA-qg22B7m7Jraac5LEIpI0MtJ4CZSjlc,47515
+ultralytics/utils/plotting.py,sha256=rumZLvfLX1bE9xQS7Gk13kVM7AmIxQOmQ5CAmhsdxCE,47531
 ultralytics/utils/tal.py,sha256=LrziY_ZHz4wln3oOnqAzgyPaXKoup17Sa103BpuaQFU,20935
-ultralytics/utils/torch_utils.py,sha256=4TCiWXepEdUdR-WPVVScS7lhMAEWCInNwfoX0XXdmo8,39181
+ultralytics/utils/torch_utils.py,sha256=i_IgmGhb5UuNlFgg4TZJrm2NSjAe_YfhGIY7Sn7cSSk,43472
 ultralytics/utils/tqdm.py,sha256=ny5RIg2OTkWQ7gdaXfYaoIgR0Xn2_hNGB6tUpO2Unns,16137
 ultralytics/utils/triton.py,sha256=fbMfTAUyoGiyslWtySzLZw53XmZJa7rF31CYFot0Wjs,5422
 ultralytics/utils/tuner.py,sha256=9D4dSIvwwxcNSJcH2QJ92qiIVi9zu-1L7_PBZ8okDyE,6816
@@ -271,11 +271,11 @@ ultralytics/utils/callbacks/mlflow.py,sha256=6K8I5zij1yq3TUW9c5BBQNqdzz3IXugQjwK
 ultralytics/utils/callbacks/neptune.py,sha256=j8pecmlcsM8FGzLKWoBw5xUsi5t8E5HuxY7TR5Um_O8,4612
 ultralytics/utils/callbacks/platform.py,sha256=a7T_8htoBB0uX1WIc392UJnhDjxkRyQMvhPYKR6wUTU,2008
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
-ultralytics/utils/callbacks/tensorboard.py,sha256=MDPBW7aDes-66OE6YqKXXvqA_EocjzEMHWGM-8z9vUQ,5281
+ultralytics/utils/callbacks/tensorboard.py,sha256=_4nfGK1dDLn6ijpvphBDhc-AS8qhS3jjY2CAWB7SNF0,5283
 ultralytics/utils/callbacks/wb.py,sha256=ngQO8EJ1kxJDF1YajScVtzBbm26jGuejA0uWeOyvf5A,7685
-ultralytics-8.3.195.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.195.dist-info/METADATA,sha256=lJa__c-le2j98HWyk_CNODxPEZVhdOOm-juC4hpZ5OU,37667
-ultralytics-8.3.195.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ultralytics-8.3.195.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.195.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.195.dist-info/RECORD,,
+ultralytics-8.3.196.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.196.dist-info/METADATA,sha256=3pZe7aM3MEicB69j31gpgBhB6rVtF7-_zwaPKINQ7us,37667
+ultralytics-8.3.196.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ultralytics-8.3.196.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.196.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.196.dist-info/RECORD,,