ultralytics 8.3.70__tar.gz → 8.3.72__tar.gz

{ultralytics-8.3.70/ultralytics.egg-info → ultralytics-8.3.72}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics
-Version: 8.3.70
+Version: 8.3.72
 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>
@@ -54,10 +54,11 @@ Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: coverage[toml]; extra == "dev"
 Requires-Dist: mkdocs>=1.6.0; extra == "dev"
+Requires-Dist: beautifulsoup4<=4.12.3; extra == "dev"
 Requires-Dist: mkdocs-material>=9.5.9; extra == "dev"
 Requires-Dist: mkdocstrings[python]; extra == "dev"
 Requires-Dist: mkdocs-redirects; extra == "dev"
-Requires-Dist: mkdocs-ultralytics-plugin>=0.1.16; extra == "dev"
+Requires-Dist: mkdocs-ultralytics-plugin>=0.1.17; extra == "dev"
 Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"
 Provides-Extra: export
 Requires-Dist: onnx>=1.12.0; extra == "export"

{ultralytics-8.3.70 → ultralytics-8.3.72}/pyproject.toml

@@ -87,10 +87,11 @@ dev = [
     "pytest-cov",
     "coverage[toml]",
     "mkdocs>=1.6.0",
+    "beautifulsoup4<=4.12.3",  # For docs https://github.com/ultralytics/ultralytics/pull/19067
     "mkdocs-material>=9.5.9",
     "mkdocstrings[python]",
     "mkdocs-redirects", # 301 redirects
-    "mkdocs-ultralytics-plugin>=0.1.16", # for meta descriptions and images, dates and authors
+    "mkdocs-ultralytics-plugin>=0.1.17", # for meta descriptions and images, dates and authors
     "mkdocs-macros-plugin>=1.0.5"  # duplicating content (i.e. export tables) in multiple places
 ]
 export = [

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.70"
+__version__ = "8.3.72"
 
 import os
 

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/cfg/models/v6/yolov6.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-activation: nn.ReLU() # (optional) model default activation function
+activation: torch.nn.ReLU() # (optional) model default activation function
 scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/engine/exporter.py

@@ -386,6 +386,8 @@ class Exporter:
             "names": model.names,
             "args": {k: v for k, v in self.args if k in fmt_keys},
         }  # model metadata
+        if dla is not None:
+            self.metadata["dla"] = dla  # make sure `AutoBackend` uses correct dla device if it has one
         if model.task == "pose":
             self.metadata["kpt_shape"] = model.model[-1].kpt_shape
 
@@ -1544,10 +1546,10 @@ class NMSModel(torch.nn.Module):
         Performs inference with NMS post-processing. Supports Detect, Segment, OBB and Pose.
 
         Args:
-            x (torch.tensor): The preprocessed tensor with shape (N, 3, H, W).
+            x (torch.Tensor): The preprocessed tensor with shape (N, 3, H, W).
 
         Returns:
-            out (torch.tensor): The post-processed results with shape (N, max_det, 4 + 2 + extra_shape).
+            out (torch.Tensor): The post-processed results with shape (N, max_det, 4 + 2 + extra_shape).
         """
         from functools import partial
 
@@ -1556,8 +1558,8 @@ class NMSModel(torch.nn.Module):
         preds = self.model(x)
         pred = preds[0] if isinstance(preds, tuple) else preds
         pred = pred.transpose(-1, -2)  # shape(1,84,6300) to shape(1,6300,84)
-        extra_shape = pred.shape[-1] - (4 + self.model.nc)  # extras from Segment, OBB, Pose
-        boxes, scores, extras = pred.split([4, self.model.nc, extra_shape], dim=2)
+        extra_shape = pred.shape[-1] - (4 + len(self.model.names))  # extras from Segment, OBB, Pose
+        boxes, scores, extras = pred.split([4, len(self.model.names), extra_shape], dim=2)
         scores, classes = scores.max(dim=-1)
         self.args.max_det = min(pred.shape[1], self.args.max_det)  # in case num_anchors < max_det
         # (N, max_det, 4 coords + 1 class score + 1 class label + extra_shape).

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/engine/model.py

@@ -11,7 +11,7 @@ from PIL import Image
 from ultralytics.cfg import TASK2DATA, get_cfg, get_save_dir
 from ultralytics.engine.results import Results
 from ultralytics.hub import HUB_WEB_ROOT, HUBTrainingSession
-from ultralytics.nn.tasks import attempt_load_one_weight, guess_model_task, nn, yaml_model_load
+from ultralytics.nn.tasks import attempt_load_one_weight, guess_model_task, yaml_model_load
 from ultralytics.utils import (
     ARGV,
     ASSETS,
@@ -26,7 +26,7 @@ from ultralytics.utils import (
 )
 
 
-class Model(nn.Module):
+class Model(torch.nn.Module):
     """
     A base class for implementing YOLO models, unifying APIs across different model types.
 
@@ -37,7 +37,7 @@ class Model(nn.Module):
     Attributes:
         callbacks (Dict): A dictionary of callback functions for various events during model operations.
         predictor (BasePredictor): The predictor object used for making predictions.
-        model (nn.Module): The underlying PyTorch model.
+        model (torch.nn.Module): The underlying PyTorch model.
         trainer (BaseTrainer): The trainer object used for training the model.
         ckpt (Dict): The checkpoint data if the model is loaded from a *.pt file.
         cfg (str): The configuration of the model if loaded from a *.yaml file.
@@ -317,7 +317,7 @@ class Model(nn.Module):
             >>> model._check_is_pytorch_model()  # Raises TypeError
         """
         pt_str = isinstance(self.model, (str, Path)) and Path(self.model).suffix == ".pt"
-        pt_module = isinstance(self.model, nn.Module)
+        pt_module = isinstance(self.model, torch.nn.Module)
         if not (pt_module or pt_str):
             raise TypeError(
                 f"model='{self.model}' should be a *.pt PyTorch model to run this method, but is a different format. "
@@ -405,7 +405,7 @@ class Model(nn.Module):
         from ultralytics import __version__
 
         updates = {
-            "model": deepcopy(self.model).half() if isinstance(self.model, nn.Module) else self.model,
+            "model": deepcopy(self.model).half() if isinstance(self.model, torch.nn.Module) else self.model,
             "date": datetime.now().isoformat(),
             "version": __version__,
             "license": "AGPL-3.0 License (https://ultralytics.com/license)",
@@ -452,7 +452,7 @@ class Model(nn.Module):
         performs both convolution and normalization in one step.
 
         Raises:
-            TypeError: If the model is not a PyTorch nn.Module.
+            TypeError: If the model is not a PyTorch torch.nn.Module.
 
         Examples:
             >>> model = Model("yolo11n.pt")
@@ -921,13 +921,13 @@ class Model(nn.Module):
         Retrieves the device on which the model's parameters are allocated.
 
         This property determines the device (CPU or GPU) where the model's parameters are currently stored. It is
-        applicable only to models that are instances of nn.Module.
+        applicable only to models that are instances of torch.nn.Module.
 
         Returns:
             (torch.device): The device (CPU/GPU) of the model.
 
         Raises:
-            AttributeError: If the model is not a PyTorch nn.Module instance.
+            AttributeError: If the model is not a torch.nn.Module instance.
 
         Examples:
             >>> model = YOLO("yolo11n.pt")
@@ -937,7 +937,7 @@ class Model(nn.Module):
             >>> print(model.device)
             device(type='cpu')
         """
-        return next(self.model.parameters()).device if isinstance(self.model, nn.Module) else None
+        return next(self.model.parameters()).device if isinstance(self.model, torch.nn.Module) else None
 
     @property
     def transforms(self):

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/engine/results.py

@@ -494,8 +494,8 @@ class Results(SimpleClass):
         Examples:
             >>> results = model("image.jpg")
             >>> for result in results:
-            ...     im = result.plot()
-            ...     im.show()
+            >>>     im = result.plot()
+            >>>     im.show()
         """
         assert color_mode in {"instance", "class"}, f"Expected color_mode='instance' or 'class', not {color_mode}."
         if img is None and isinstance(self.orig_img, torch.Tensor):
@@ -600,7 +600,7 @@ class Results(SimpleClass):
             >>> results = model("path/to/image.jpg")
             >>> results[0].show()  # Display the first result
             >>> for result in results:
-            ...     result.show()  # Display all results
+            >>>     result.show()  # Display all results
         """
         self.plot(show=True, *args, **kwargs)
 
@@ -620,10 +620,10 @@ class Results(SimpleClass):
         Examples:
             >>> results = model("path/to/image.jpg")
             >>> for result in results:
-            ...     result.save("annotated_image.jpg")
+            >>>     result.save("annotated_image.jpg")
             >>> # Or with custom plot arguments
             >>> for result in results:
-            ...     result.save("annotated_image.jpg", conf=False, line_width=2)
+            >>>     result.save("annotated_image.jpg", conf=False, line_width=2)
         """
         if not filename:
             filename = f"results_{Path(self.path).name}"
@@ -644,7 +644,7 @@ class Results(SimpleClass):
         Examples:
             >>> results = model("path/to/image.jpg")
             >>> for result in results:
-            ...     print(result.verbose())
+            >>>     print(result.verbose())
             2 persons, 1 car, 3 traffic lights,
             dog 0.92, cat 0.78, horse 0.64,
 
@@ -681,7 +681,7 @@ class Results(SimpleClass):
             >>> model = YOLO("yolo11n.pt")
             >>> results = model("path/to/image.jpg")
             >>> for result in results:
-            ...     result.save_txt("output.txt")
+            >>>     result.save_txt("output.txt")
 
         Notes:
             - The file will contain one line per detection or classification with the following structure:
@@ -740,7 +740,7 @@ class Results(SimpleClass):
         Examples:
             >>> results = model("path/to/image.jpg")
             >>> for result in results:
-            ...     result.save_crop(save_dir="path/to/crops", file_name="detection")
+            >>>     result.save_crop(save_dir="path/to/crops", file_name="detection")
         """
         if self.probs is not None:
             LOGGER.warning("WARNING ⚠️ Classify task do not support `save_crop`.")
@@ -776,8 +776,9 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("image.jpg")
-            >>> summary = results[0].summary()
-            >>> print(summary)
+            >>> for result in results:
+            >>>     summary = result.summary()
+            >>>     print(summary)
         """
         # Create list of detection dictionaries
         results = []
@@ -839,8 +840,9 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("path/to/image.jpg")
-            >>> df_result = results[0].to_df()
-            >>> print(df_result)
+            >>> for result in results:
+            >>>     df_result = result.to_df()
+            >>>     print(df_result)
         """
         import pandas as pd  # scope for faster 'import ultralytics'
 
@@ -867,8 +869,9 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("path/to/image.jpg")
-            >>> csv_result = results[0].to_csv()
-            >>> print(csv_result)
+            >>> for result in results:
+            >>>     csv_result = result.to_csv()
+            >>>     print(csv_result)
         """
         return self.to_df(normalize=normalize, decimals=decimals).to_csv(*args, **kwargs)
 
@@ -892,8 +895,9 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("path/to/image.jpg")
-            >>> xml_result = results[0].to_xml()
-            >>> print(xml_result)
+            >>> for result in results:
+            >>>     xml_result = result.to_xml()
+            >>>     print(xml_result)
         """
         check_requirements("lxml")
         df = self.to_df(normalize=normalize, decimals=decimals)
@@ -922,8 +926,9 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("path/to/image.jpg")
-            >>> json_result = results[0].to_json()
-            >>> print(json_result)
+            >>> for result in results:
+            >>>     json_result = result.to_json()
+            >>>     print(json_result)
 
         Notes:
             - For classification tasks, the JSON will contain class probabilities instead of bounding boxes.
@@ -954,8 +959,8 @@ class Results(SimpleClass):
 
         Examples:
             >>> results = model("path/to/image.jpg")
-            >>> results[0].to_sql()
-            >>> print("SQL data written successfully.")
+            >>> for result in results:
+            >>>     result.to_sql()
         """
         import json
         import sqlite3

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/models/sam/modules/sam.py

@@ -426,8 +426,7 @@ class SAM2Model(torch.nn.Module):
                 high_res_masks: Tensor of shape (B, 1, H*16, W*16) with the best high-resolution mask.
                 obj_ptr: Tensor of shape (B, C) with object pointer vector for the output mask.
                 object_score_logits: Tensor of shape (B) with object score logits.
-
-            Where M is 3 if multimask_output=True, and 1 if multimask_output=False.
+                Where M is 3 if multimask_output=True, and 1 if multimask_output=False.
 
         Examples:
             >>> backbone_features = torch.rand(1, 256, 32, 32)

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/models/yolo/pose/val.py

@@ -158,7 +158,7 @@ class PoseValidator(DetectionValidator):
             gt_kpts (torch.Tensor | None): Optional tensor with shape (N, 51) representing ground truth keypoints.
 
         Returns:
-            torch.Tensor: A tensor with shape (N, 10) representing the correct prediction matrix for 10 IoU levels,
+            (torch.Tensor): A tensor with shape (N, 10) representing the correct prediction matrix for 10 IoU levels,
                 where N is the number of detections.
 
         Example:

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/nn/autobackend.py

@@ -292,13 +292,10 @@ class AutoBackend(nn.Module):
                     metadata = json.loads(f.read(meta_len).decode("utf-8"))  # read metadata
                 except UnicodeDecodeError:
                     f.seek(0)  # engine file may lack embedded Ultralytics metadata
+                dla = metadata.get("dla", None)
+                if dla is not None:
+                    runtime.DLA_core = int(dla)
                 model = runtime.deserialize_cuda_engine(f.read())  # read engine
-                if "dla" in str(device.type):
-                    dla_core = int(device.type.split(":")[1])
-                    assert dla_core in {0, 1}, (
-                        "Expected device type for inference in DLA is 'dla:0' or 'dla:1', but received '{device.type}'"
-                    )
-                    runtime.DLA_core = dla_core
 
             # Model context
             try:
@@ -780,7 +777,7 @@ class AutoBackend(nn.Module):
         saved_model, pb, tflite, edgetpu, tfjs, ncnn or paddle.
 
         Args:
-            p: path to the model file. Defaults to path/to/model.pt
+            p (str): path to the model file. Defaults to path/to/model.pt
 
         Examples:
             >>> model = AutoBackend(weights="path/to/model.onnx")

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/nn/tasks.py

@@ -9,7 +9,6 @@ from pathlib import Path
 
 import thop
 import torch
-import torch.nn as nn
 
 from ultralytics.nn.modules import (
     AIFI,
@@ -88,7 +87,7 @@ from ultralytics.utils.torch_utils import (
 )
 
 
-class BaseModel(nn.Module):
+class BaseModel(torch.nn.Module):
     """The BaseModel class serves as a base class for all the models in the Ultralytics YOLO family."""
 
     def forward(self, x, *args, **kwargs):
@@ -151,7 +150,7 @@ class BaseModel(nn.Module):
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
             if embed and m.i in embed:
-                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
+                embeddings.append(torch.nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                 if m.i == max(embed):
                     return torch.unbind(torch.cat(embeddings, 1), dim=0)
         return x
@@ -170,12 +169,9 @@ class BaseModel(nn.Module):
         the provided list.
 
         Args:
-            m (nn.Module): The layer to be profiled.
+            m (torch.nn.Module): The layer to be profiled.
             x (torch.Tensor): The input data to the layer.
             dt (list): A list to store the computation time of the layer.
-
-        Returns:
-            None
         """
         c = m == self.model[-1] and isinstance(x, list)  # is final layer list, copy input as inplace fix
         flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1e9 * 2 if thop else 0  # GFLOPs
@@ -195,7 +191,7 @@ class BaseModel(nn.Module):
         computation efficiency.
 
         Returns:
-            (nn.Module): The fused model is returned.
+            (torch.nn.Module): The fused model is returned.
         """
         if not self.is_fused():
             for m in self.model.modules():
@@ -229,7 +225,7 @@ class BaseModel(nn.Module):
         Returns:
             (bool): True if the number of BatchNorm layers in the model is less than the threshold, False otherwise.
         """
-        bn = tuple(v for k, v in nn.__dict__.items() if "Norm" in k)  # normalization layers, i.e. BatchNorm2d()
+        bn = tuple(v for k, v in torch.nn.__dict__.items() if "Norm" in k)  # normalization layers, i.e. BatchNorm2d()
         return sum(isinstance(v, bn) for v in self.modules()) < thresh  # True if < 'thresh' BatchNorm layers in model
 
     def info(self, detailed=False, verbose=True, imgsz=640):
@@ -304,7 +300,7 @@ class DetectionModel(BaseModel):
         self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict
         if self.yaml["backbone"][0][2] == "Silence":
             LOGGER.warning(
-                "WARNING ⚠️ YOLOv9 `Silence` module is deprecated in favor of nn.Identity. "
+                "WARNING ⚠️ YOLOv9 `Silence` module is deprecated in favor of torch.nn.Identity. "
                 "Please delete local *.pt file and re-download the latest model checkpoint."
             )
             self.yaml["backbone"][0][2] = "nn.Identity"
@@ -458,20 +454,22 @@ class ClassificationModel(BaseModel):
         name, m = list((model.model if hasattr(model, "model") else model).named_children())[-1]  # last module
         if isinstance(m, Classify):  # YOLO Classify() head
             if m.linear.out_features != nc:
-                m.linear = nn.Linear(m.linear.in_features, nc)
-        elif isinstance(m, nn.Linear):  # ResNet, EfficientNet
+                m.linear = torch.nn.Linear(m.linear.in_features, nc)
+        elif isinstance(m, torch.nn.Linear):  # ResNet, EfficientNet
             if m.out_features != nc:
-                setattr(model, name, nn.Linear(m.in_features, nc))
-        elif isinstance(m, nn.Sequential):
+                setattr(model, name, torch.nn.Linear(m.in_features, nc))
+        elif isinstance(m, torch.nn.Sequential):
             types = [type(x) for x in m]
-            if nn.Linear in types:
-                i = len(types) - 1 - types[::-1].index(nn.Linear)  # last nn.Linear index
+            if torch.nn.Linear in types:
+                i = len(types) - 1 - types[::-1].index(torch.nn.Linear)  # last torch.nn.Linear index
                 if m[i].out_features != nc:
-                    m[i] = nn.Linear(m[i].in_features, nc)
-            elif nn.Conv2d in types:
-                i = len(types) - 1 - types[::-1].index(nn.Conv2d)  # last nn.Conv2d index
+                    m[i] = torch.nn.Linear(m[i].in_features, nc)
+            elif torch.nn.Conv2d in types:
+                i = len(types) - 1 - types[::-1].index(torch.nn.Conv2d)  # last torch.nn.Conv2d index
                 if m[i].out_channels != nc:
-                    m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)
+                    m[i] = torch.nn.Conv2d(
+                        m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None
+                    )
 
     def init_criterion(self):
         """Initialize the loss criterion for the ClassificationModel."""
@@ -486,12 +484,6 @@ class RTDETRDetectionModel(DetectionModel):
     the training and inference processes. RTDETR is an object detection and tracking model that extends from the
     DetectionModel base class.
 
-    Attributes:
-        cfg (str): The configuration file path or preset string. Default is 'rtdetr-l.yaml'.
-        ch (int): Number of input channels. Default is 3 (RGB).
-        nc (int, optional): Number of classes for object detection. Default is None.
-        verbose (bool): Specifies if summary statistics are shown during initialization. Default is True.
-
     Methods:
         init_criterion: Initializes the criterion used for loss calculation.
         loss: Computes and returns the loss during training.
@@ -587,7 +579,7 @@ class RTDETRDetectionModel(DetectionModel):
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
             if embed and m.i in embed:
-                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
+                embeddings.append(torch.nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                 if m.i == max(embed):
                     return torch.unbind(torch.cat(embeddings, 1), dim=0)
         head = self.model[-1]
@@ -663,7 +655,7 @@ class WorldModel(DetectionModel):
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
             if embed and m.i in embed:
-                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
+                embeddings.append(torch.nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                 if m.i == max(embed):
                     return torch.unbind(torch.cat(embeddings, 1), dim=0)
         return x
@@ -684,7 +676,7 @@ class WorldModel(DetectionModel):
         return self.criterion(preds, batch)
 
 
-class Ensemble(nn.ModuleList):
+class Ensemble(torch.nn.ModuleList):
     """Ensemble of models."""
 
     def __init__(self):
@@ -887,7 +879,7 @@ def attempt_load_weights(weights, device=None, inplace=True, fuse=False):
     for m in ensemble.modules():
         if hasattr(m, "inplace"):
             m.inplace = inplace
-        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
+        elif isinstance(m, torch.nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
             m.recompute_scale_factor = None  # torch 1.11.0 compatibility
 
     # Return model
@@ -922,7 +914,7 @@ def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False):
     for m in model.modules():
         if hasattr(m, "inplace"):
             m.inplace = inplace
-        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
+        elif isinstance(m, torch.nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
             m.recompute_scale_factor = None  # torch 1.11.0 compatibility
 
     # Return model and ckpt
@@ -946,7 +938,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
         depth, width, max_channels = scales[scale]
 
     if act:
-        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
+        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = torch.nn.SiLU()
         if verbose:
             LOGGER.info(f"{colorstr('activation:')} {act}")  # print
 
@@ -982,7 +974,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             C3,
             C3TR,
             C3Ghost,
-            nn.ConvTranspose2d,
+            torch.nn.ConvTranspose2d,
             DWConvTranspose2d,
             C3x,
             RepC3,
@@ -1048,7 +1040,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
                 n = 1
         elif m is ResNetLayer:
             c2 = args[1] if args[3] else args[1] * 4
-        elif m is nn.BatchNorm2d:
+        elif m is torch.nn.BatchNorm2d:
             args = [ch[f]]
         elif m is Concat:
             c2 = sum(ch[x] for x in f)
@@ -1073,7 +1065,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
         else:
             c2 = ch[f]
 
-        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        m_ = torch.nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
         t = str(m)[8:-2].replace("__main__.", "")  # module type
         m_.np = sum(x.numel() for x in m_.parameters())  # number params
         m_.i, m_.f, m_.type = i, f, t  # attach index, 'from' index, type
@@ -1084,7 +1076,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
         if i == 0:
             ch = []
         ch.append(c2)
-    return nn.Sequential(*layers), sorted(save)
+    return torch.nn.Sequential(*layers), sorted(save)
 
 
 def yaml_model_load(path):
@@ -1126,7 +1118,7 @@ def guess_model_task(model):
     Guess the task of a PyTorch model from its architecture or configuration.
 
     Args:
-        model (nn.Module | dict): PyTorch model or model configuration in YAML format.
+        model (torch.nn.Module | dict): PyTorch model or model configuration in YAML format.
 
     Returns:
         (str): Task of the model ('detect', 'segment', 'classify', 'pose').
@@ -1154,7 +1146,7 @@ def guess_model_task(model):
         with contextlib.suppress(Exception):
             return cfg2task(model)
     # Guess from PyTorch model
-    if isinstance(model, nn.Module):  # PyTorch model
+    if isinstance(model, torch.nn.Module):  # PyTorch model
         for x in "model.args", "model.model.args", "model.model.model.args":
             with contextlib.suppress(Exception):
                 return eval(x)["task"]

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics/utils/plotting.py

@@ -801,9 +801,8 @@ class Annotator:
             return
 
         cv2.polylines(self.im, [np.int32([mask])], isClosed=True, color=mask_color, thickness=2)
-        text_size, _ = cv2.getTextSize(label, 0, self.sf, self.tf)
-
         if label:
+            text_size, _ = cv2.getTextSize(label, 0, self.sf, self.tf)
             cv2.rectangle(
                 self.im,
                 (int(mask[0][0]) - text_size[0] // 2 - 10, int(mask[0][1]) - text_size[1] - 10),

{ultralytics-8.3.70 → ultralytics-8.3.72/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics
-Version: 8.3.70
+Version: 8.3.72
 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>
@@ -54,10 +54,11 @@ Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: coverage[toml]; extra == "dev"
 Requires-Dist: mkdocs>=1.6.0; extra == "dev"
+Requires-Dist: beautifulsoup4<=4.12.3; extra == "dev"
 Requires-Dist: mkdocs-material>=9.5.9; extra == "dev"
 Requires-Dist: mkdocstrings[python]; extra == "dev"
 Requires-Dist: mkdocs-redirects; extra == "dev"
-Requires-Dist: mkdocs-ultralytics-plugin>=0.1.16; extra == "dev"
+Requires-Dist: mkdocs-ultralytics-plugin>=0.1.17; extra == "dev"
 Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"
 Provides-Extra: export
 Requires-Dist: onnx>=1.12.0; extra == "export"

{ultralytics-8.3.70 → ultralytics-8.3.72}/ultralytics.egg-info/requires.txt

@@ -23,10 +23,11 @@ pytest
 pytest-cov
 coverage[toml]
 mkdocs>=1.6.0
+beautifulsoup4<=4.12.3
 mkdocs-material>=9.5.9
 mkdocstrings[python]
 mkdocs-redirects
-mkdocs-ultralytics-plugin>=0.1.16
+mkdocs-ultralytics-plugin>=0.1.17
 mkdocs-macros-plugin>=1.0.5
 
 [export]