ultralytics 8.2.70__tar.gz → 8.2.72__tar.gz

{ultralytics-8.2.70/ultralytics.egg-info → ultralytics-8.2.72}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.70
+Version: 8.2.72
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu

{ultralytics-8.2.70 → ultralytics-8.2.72}/tests/test_cli.py

@@ -8,6 +8,7 @@ from PIL import Image
 from tests import CUDA_DEVICE_COUNT, CUDA_IS_AVAILABLE
 from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
 from ultralytics.utils import ASSETS, WEIGHTS_DIR, checks
+from ultralytics.utils.torch_utils import TORCH_1_9
 
 # Constants
 TASK_MODEL_DATA = [(task, WEIGHTS_DIR / TASK2MODEL[task], TASK2DATA[task]) for task in TASKS]
@@ -57,6 +58,8 @@ def test_rtdetr(task="detect", model="yolov8n-rtdetr.yaml", data="coco8.yaml"):
     # Warning: must use imgsz=640 (note also add coma, spaces, fraction=0.25 args to test single-image training)
     run(f"yolo train {task} model={model} data={data} --imgsz= 160 epochs =1, cache = disk fraction=0.25")
     run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
+    if TORCH_1_9:
+        run(f"yolo predict {task} model='rtdetr-l.pt' source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM with CLIP is not supported in Python 3.12")

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.70"
+__version__ = "8.2.72"
 
 import os
 

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/data/converter.py

@@ -334,6 +334,87 @@ def convert_coco(
     LOGGER.info(f"{'LVIS' if lvis else 'COCO'} data converted successfully.\nResults saved to {save_dir.resolve()}")
 
 
+def convert_segment_masks_to_yolo_seg(masks_dir, output_dir, classes):
+    """
+    Converts a dataset of segmentation mask images to the YOLO segmentation format.
+
+    This function takes the directory containing the binary format mask images and converts them into YOLO segmentation format.
+    The converted masks are saved in the specified output directory.
+
+    Args:
+        masks_dir (str): The path to the directory where all mask images (png, jpg) are stored.
+        output_dir (str): The path to the directory where the converted YOLO segmentation masks will be stored.
+        classes (int): Total classes in the dataset i.e for COCO classes=80
+
+    Example:
+        ```python
+        from ultralytics.data.converter import convert_segment_masks_to_yolo_seg
+
+        # for coco dataset, we have 80 classes
+        convert_segment_masks_to_yolo_seg('path/to/masks_directory', 'path/to/output/directory', classes=80)
+        ```
+
+    Notes:
+        The expected directory structure for the masks is:
+
+            - masks
+                ├─ mask_image_01.png or mask_image_01.jpg
+                ├─ mask_image_02.png or mask_image_02.jpg
+                ├─ mask_image_03.png or mask_image_03.jpg
+                └─ mask_image_04.png or mask_image_04.jpg
+
+        After execution, the labels will be organized in the following structure:
+
+            - output_dir
+                ├─ mask_yolo_01.txt
+                ├─ mask_yolo_02.txt
+                ├─ mask_yolo_03.txt
+                └─ mask_yolo_04.txt
+    """
+    import os
+
+    pixel_to_class_mapping = {i + 1: i for i in range(80)}
+    for mask_filename in os.listdir(masks_dir):
+        if mask_filename.endswith(".png"):
+            mask_path = os.path.join(masks_dir, mask_filename)
+            mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)  # Read the mask image in grayscale
+            img_height, img_width = mask.shape  # Get image dimensions
+            LOGGER.info(f"Processing {mask_path} imgsz = {img_height} x {img_width}")
+
+            unique_values = np.unique(mask)  # Get unique pixel values representing different classes
+            yolo_format_data = []
+
+            for value in unique_values:
+                if value == 0:
+                    continue  # Skip background
+                class_index = pixel_to_class_mapping.get(value, -1)
+                if class_index == -1:
+                    LOGGER.warning(f"Unknown class for pixel value {value} in file {mask_filename}, skipping.")
+                    continue
+
+                # Create a binary mask for the current class and find contours
+                contours, _ = cv2.findContours(
+                    (mask == value).astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
+                )  # Find contours
+
+                for contour in contours:
+                    if len(contour) >= 3:  # YOLO requires at least 3 points for a valid segmentation
+                        contour = contour.squeeze()  # Remove single-dimensional entries
+                        yolo_format = [class_index]
+                        for point in contour:
+                            # Normalize the coordinates
+                            yolo_format.append(round(point[0] / img_width, 6))  # Rounding to 6 decimal places
+                            yolo_format.append(round(point[1] / img_height, 6))
+                        yolo_format_data.append(yolo_format)
+            # Save Ultralytics YOLO format data to file
+            output_path = os.path.join(output_dir, os.path.splitext(mask_filename)[0] + ".txt")
+            with open(output_path, "w") as file:
+                for item in yolo_format_data:
+                    line = " ".join(map(str, item))
+                    file.write(line + "\n")
+            LOGGER.info(f"Processed and stored at {output_path} imgsz = {img_height} x {img_width}")
+
+
 def convert_dota_to_yolo_obb(dota_root_path: str):
     """
     Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format.

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/engine/trainer.py

@@ -26,6 +26,7 @@ from ultralytics.data.utils import check_cls_dataset, check_det_dataset
 from ultralytics.nn.tasks import attempt_load_one_weight, attempt_load_weights
 from ultralytics.utils import (
     DEFAULT_CFG,
+    LOCAL_RANK,
     LOGGER,
     RANK,
     TQDM,
@@ -129,7 +130,7 @@ class BaseTrainer:
 
         # Model and Dataset
         self.model = check_model_file_from_stem(self.args.model)  # add suffix, i.e. yolov8n -> yolov8n.pt
-        with torch_distributed_zero_first(RANK):  # avoid auto-downloading dataset multiple times
+        with torch_distributed_zero_first(LOCAL_RANK):  # avoid auto-downloading dataset multiple times
             self.trainset, self.testset = self.get_dataset()
         self.ema = None
 
@@ -285,7 +286,7 @@ class BaseTrainer:
 
         # Dataloaders
         batch_size = self.batch_size // max(world_size, 1)
-        self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode="train")
+        self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=LOCAL_RANK, mode="train")
         if RANK in {-1, 0}:
             # Note: When training DOTA dataset, double batch size could get OOM on images with >2000 objects.
             self.test_loader = self.get_dataloader(

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/engine/validator.py

@@ -136,8 +136,8 @@ class BaseValidator:
             if engine:
                 self.args.batch = model.batch_size
             elif not pt and not jit:
-                self.args.batch = 1  # export.py models default to batch-size 1
-                LOGGER.info(f"Forcing batch=1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models")
+                self.args.batch = model.metadata.get("batch", 1)  # export.py models default to batch-size 1
+                LOGGER.info(f"Setting batch={self.args.batch} input of shape ({self.args.batch}, 3, {imgsz}, {imgsz})")
 
             if str(self.args.data).split(".")[-1] in {"yaml", "yml"}:
                 self.data = check_det_dataset(self.args.data)

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/models/sam2/predict.py

@@ -102,28 +102,23 @@ class SAM2Predictor(Predictor):
         if bboxes is not None:
             bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
             bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes *= r
+            bboxes = bboxes.view(-1, 2, 2) * r
+            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
+            # NOTE: merge "boxes" and "points" into a single "points" input
+            # (where boxes are added at the beginning) to model.sam_prompt_encoder
+            if points is not None:
+                points = torch.cat([bboxes, points], dim=1)
+                labels = torch.cat([bbox_labels, labels], dim=1)
+            else:
+                points, labels = bboxes, bbox_labels
         if masks is not None:
             masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
 
         points = (points, labels) if points is not None else None
-        # TODO: Embed prompts
-        # if bboxes is not None:
-        #     box_coords = bboxes.reshape(-1, 2, 2)
-        #     box_labels = torch.tensor([[2, 3]], dtype=torch.int, device=bboxes.device)
-        #     box_labels = box_labels.repeat(bboxes.size(0), 1)
-        #     # we merge "boxes" and "points" into a single "concat_points" input (where
-        #     # boxes are added at the beginning) to sam_prompt_encoder
-        #     if concat_points is not None:
-        #         concat_coords = torch.cat([box_coords, concat_points[0]], dim=1)
-        #         concat_labels = torch.cat([box_labels, concat_points[1]], dim=1)
-        #         concat_points = (concat_coords, concat_labels)
-        #     else:
-        #         concat_points = (box_coords, box_labels)
 
         sparse_embeddings, dense_embeddings = self.model.sam_prompt_encoder(
             points=points,
-            boxes=bboxes,
+            boxes=None,
             masks=masks,
         )
         # Predict masks

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/nn/modules/transformer.py

@@ -186,8 +186,8 @@ class MLP(nn.Module):
     def forward(self, x):
         """Forward pass for the entire MLP."""
         for i, layer in enumerate(self.layers):
-            x = self.act(layer(x)) if i < self.num_layers - 1 else layer(x)
-        return x.sigmoid() if self.sigmoid else x
+            x = getattr(self, "act", nn.ReLU())(layer(x)) if i < self.num_layers - 1 else layer(x)
+        return x.sigmoid() if getattr(self, "sigmoid", False) else x
 
 
 class LayerNorm2d(nn.Module):

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/utils/__init__.py

@@ -47,7 +47,7 @@ PYTHON_VERSION = platform.python_version()
 TORCH_VERSION = torch.__version__
 TORCHVISION_VERSION = importlib.metadata.version("torchvision")  # faster than importing torchvision
 HELP_MSG = """
-    Usage examples for running YOLOv8:
+    Usage examples for running Ultralytics YOLO:
 
     1. Install the ultralytics package:
 
@@ -58,25 +58,25 @@ HELP_MSG = """
         from ultralytics import YOLO
 
         # Load a model
-        model = YOLO('yolov8n.yaml')  # build a new model from scratch
+        model = YOLO("yolov8n.yaml")  # build a new model from scratch
         model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)
 
         # Use the model
         results = model.train(data="coco8.yaml", epochs=3)  # train the model
         results = model.val()  # evaluate model performance on the validation set
-        results = model('https://ultralytics.com/images/bus.jpg')  # predict on an image
-        success = model.export(format='onnx')  # export the model to ONNX format
+        results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
+        success = model.export(format="onnx")  # export the model to ONNX format
 
     3. Use the command line interface (CLI):
 
-        YOLOv8 'yolo' CLI commands use the following syntax:
+        Ultralytics 'yolo' CLI commands use the following syntax:
 
             yolo TASK MODE ARGS
 
-            Where   TASK (optional) is one of [detect, segment, classify]
-                    MODE (required) is one of [train, val, predict, export]
-                    ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
-                        See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
+            Where   TASK (optional) is one of [detect, segment, classify, pose, obb]
+                    MODE (required) is one of [train, val, predict, export, benchmark]
+                    ARGS (optional) are any number of custom "arg=value" pairs like "imgsz=320" that override defaults.
+                        See all ARGS at https://docs.ultralytics.com/usage/cfg or with "yolo cfg"
 
         - Train a detection model for 10 epochs with an initial learning_rate of 0.01
             yolo detect train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/utils/downloads.py

@@ -41,7 +41,7 @@ def is_url(url, check=False):
     Args:
         url (str): The string to be validated as a URL.
         check (bool, optional): If True, performs an additional check to see if the URL exists online.
-            Defaults to True.
+            Defaults to False.
 
     Returns:
         (bool): Returns True for a valid URL. If 'check' is True, also returns True if the URL exists online.
@@ -201,7 +201,7 @@ def check_disk_space(url="https://ultralytics.com/assets/coco8.zip", path=Path.c
     Args:
         url (str, optional): The URL to the file. Defaults to 'https://ultralytics.com/assets/coco8.zip'.
         path (str | Path, optional): The path or drive to check the available free space on.
-        sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 2.0.
+        sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 1.5.
         hard (bool, optional): Whether to throw an error or not on insufficient disk space. Defaults to True.
 
     Returns:

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/utils/ops.py

@@ -528,7 +528,7 @@ def ltwh2xywh(x):
 def xyxyxyxy2xywhr(x):
     """
     Convert batched Oriented Bounding Boxes (OBB) from [xy1, xy2, xy3, xy4] to [xywh, rotation]. Rotation values are
-    expected in degrees from 0 to 90.
+    returned in radians from 0 to pi/2.
 
     Args:
         x (numpy.ndarray | torch.Tensor): Input box corners [xy1, xy2, xy3, xy4] of shape (n, 8).
@@ -551,7 +551,7 @@ def xyxyxyxy2xywhr(x):
 def xywhr2xyxyxyxy(x):
     """
     Convert batched Oriented Bounding Boxes (OBB) from [xywh, rotation] to [xy1, xy2, xy3, xy4]. Rotation values should
-    be in degrees from 0 to 90.
+    be in radians from 0 to pi/2.
 
     Args:
         x (numpy.ndarray | torch.Tensor): Boxes in [cx, cy, w, h, rotation] format of shape (n, 5) or (b, n, 5).

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/utils/plotting.py

@@ -195,12 +195,12 @@ class Annotator:
 
     def circle_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=2):
         """
-        Draws a label with a background rectangle centered within a given bounding box.
+        Draws a label with a background circle centered within a given bounding box.
 
         Args:
             box (tuple): The bounding box coordinates (x1, y1, x2, y2).
             label (str): The text label to be displayed.
-            color (tuple, optional): The background color of the rectangle (R, G, B).
+            color (tuple, optional): The background color of the rectangle (B, G, R).
             txt_color (tuple, optional): The color of the text (R, G, B).
             margin (int, optional): The margin between the text and the rectangle border.
         """
@@ -242,7 +242,7 @@ class Annotator:
         Args:
             box (tuple): The bounding box coordinates (x1, y1, x2, y2).
             label (str): The text label to be displayed.
-            color (tuple, optional): The background color of the rectangle (R, G, B).
+            color (tuple, optional): The background color of the rectangle (B, G, R).
             txt_color (tuple, optional): The color of the text (R, G, B).
             margin (int, optional): The margin between the text and the rectangle border.
         """
@@ -280,7 +280,7 @@ class Annotator:
         Args:
             box (tuple): The bounding box coordinates (x1, y1, x2, y2).
             label (str): The text label to be displayed.
-            color (tuple, optional): The background color of the rectangle (R, G, B).
+            color (tuple, optional): The background color of the rectangle (B, G, R).
             txt_color (tuple, optional): The color of the text (R, G, B).
             rotated (bool, optional): Variable used to check if task is OBB
         """

{ultralytics-8.2.70 → ultralytics-8.2.72}/ultralytics/utils/torch_utils.py

@@ -48,11 +48,12 @@ TORCHVISION_0_18 = check_version(TORCHVISION_VERSION, "0.18.0")
 def torch_distributed_zero_first(local_rank: int):
     """Ensures all processes in distributed training wait for the local master (rank 0) to complete a task first."""
     initialized = dist.is_available() and dist.is_initialized()
+
     if initialized and local_rank not in {-1, 0}:
         dist.barrier(device_ids=[local_rank])
     yield
     if initialized and local_rank == 0:
-        dist.barrier(device_ids=[0])
+        dist.barrier(device_ids=[local_rank])
 
 
 def smart_inference_mode():

{ultralytics-8.2.70 → ultralytics-8.2.72/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.70
+Version: 8.2.72
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu