dgenerate-ultralytics-headless 8.4.5__tar.gz → 8.4.7__tar.gz

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.4.5
+Version: 8.4.7
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -39,8 +39,8 @@ Requires-Dist: pillow>=7.1.2
 Requires-Dist: pyyaml>=5.3.1
 Requires-Dist: requests>=2.23.0
 Requires-Dist: scipy>=1.4.1
-Requires-Dist: torch>=1.8.0
-Requires-Dist: torch!=2.4.0,>=1.8.0; sys_platform == "win32"
+Requires-Dist: torch<2.10,>=1.8.0
+Requires-Dist: torch!=2.4.0,<2.10,>=1.8.0; sys_platform == "win32"
 Requires-Dist: torchvision>=0.9.0
 Requires-Dist: psutil>=5.8.0
 Requires-Dist: polars>=0.20.0

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/dgenerate_ultralytics_headless.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.4.5
+Version: 8.4.7
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -39,8 +39,8 @@ Requires-Dist: pillow>=7.1.2
 Requires-Dist: pyyaml>=5.3.1
 Requires-Dist: requests>=2.23.0
 Requires-Dist: scipy>=1.4.1
-Requires-Dist: torch>=1.8.0
-Requires-Dist: torch!=2.4.0,>=1.8.0; sys_platform == "win32"
+Requires-Dist: torch<2.10,>=1.8.0
+Requires-Dist: torch!=2.4.0,<2.10,>=1.8.0; sys_platform == "win32"
 Requires-Dist: torchvision>=0.9.0
 Requires-Dist: psutil>=5.8.0
 Requires-Dist: polars>=0.20.0

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/dgenerate_ultralytics_headless.egg-info/SOURCES.txt

@@ -45,6 +45,7 @@ ultralytics/cfg/datasets/brain-tumor.yaml
 ultralytics/cfg/datasets/carparts-seg.yaml
 ultralytics/cfg/datasets/coco-pose.yaml
 ultralytics/cfg/datasets/coco.yaml
+ultralytics/cfg/datasets/coco12-formats.yaml
 ultralytics/cfg/datasets/coco128-seg.yaml
 ultralytics/cfg/datasets/coco128.yaml
 ultralytics/cfg/datasets/coco8-grayscale.yaml

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/dgenerate_ultralytics_headless.egg-info/requires.txt

@@ -5,14 +5,14 @@ pillow>=7.1.2
 pyyaml>=5.3.1
 requests>=2.23.0
 scipy>=1.4.1
-torch>=1.8.0
+torch<2.10,>=1.8.0
 torchvision>=0.9.0
 psutil>=5.8.0
 polars>=0.20.0
 ultralytics-thop>=2.0.18
 
 [:sys_platform == "win32"]
-torch!=2.4.0,>=1.8.0
+torch!=2.4.0,<2.10,>=1.8.0
 
 [dev]
 ipython

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/pyproject.toml

@@ -68,8 +68,8 @@ dependencies = [
     "pyyaml>=5.3.1",
     "requests>=2.23.0",
     "scipy>=1.4.1",
-    "torch>=1.8.0",
-    "torch>=1.8.0,!=2.4.0; sys_platform == 'win32'", # Windows CPU errors w/ 2.4.0 https://github.com/ultralytics/ultralytics/issues/15049
+    "torch>=1.8.0,<2.10",
+    "torch>=1.8.0,<2.10,!=2.4.0; sys_platform == 'win32'", # Windows CPU errors w/ 2.4.0 https://github.com/ultralytics/ultralytics/issues/15049
     "torchvision>=0.9.0",
     "psutil>=5.8.0", # system utilization
     "polars>=0.20.0",

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/tests/test_python.py

@@ -159,6 +159,30 @@ def test_predict_gray_and_4ch(tmp_path):
         f.unlink()  # cleanup
 
 
+@pytest.mark.slow
+@pytest.mark.skipif(not ONLINE, reason="environment is offline")
+def test_predict_all_image_formats():
+    """Test YOLO prediction all 12 image formats (AVIF, BMP, DNG, HEIC, JP2, JPEG, JPG, MPO, PNG, TIF, TIFF, WebP)."""
+    # Download dataset if needed
+    data = check_det_dataset("coco12-formats.yaml")
+    dataset_path = Path(data["path"])
+
+    # Collect all images from train and val
+    images = list((dataset_path / "images" / "train").glob("*.*"))
+    images += list((dataset_path / "images" / "val").glob("*.*"))
+    assert len(images) == 12, f"Expected 12 images, found {len(images)}"
+
+    # Verify all format extensions are represented
+    extensions = {img.suffix.lower().lstrip(".") for img in images}
+    expected = {"avif", "bmp", "dng", "heic", "jp2", "jpeg", "jpg", "mpo", "png", "tif", "tiff", "webp"}
+    assert extensions == expected, f"Missing formats: {expected - extensions}"
+
+    # Run inference on all images
+    model = YOLO(MODEL)
+    results = model(images, imgsz=32)
+    assert len(results) == 12, f"Expected 12 results, got {len(results)}"
+
+
 @pytest.mark.slow
 @pytest.mark.skipif(not ONLINE, reason="environment is offline")
 @pytest.mark.skipif(is_github_action_running(), reason="No auth https://github.com/JuanBindez/pytubefix/issues/166")
@@ -209,11 +233,12 @@ def test_val(task: str, weight: str, data: str) -> None:
         metrics.confusion_matrix.to_json()
 
 
+@pytest.mark.skipif(not ONLINE, reason="environment is offline")
 @pytest.mark.skipif(IS_JETSON or IS_RASPBERRYPI, reason="Edge devices not intended for training")
 def test_train_scratch():
-    """Test training the YOLO model from scratch using the provided configuration."""
+    """Test training the YOLO model from scratch on 12 different image types in the COCO12-Formats dataset."""
     model = YOLO(CFG)
-    model.train(data="coco8.yaml", epochs=2, imgsz=32, cache="disk", batch=-1, close_mosaic=1, name="model")
+    model.train(data="coco12-formats.yaml", epochs=2, imgsz=32, cache="disk", batch=-1, close_mosaic=1, name="model")
     model(SOURCE)
 
 

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.4.5"
+__version__ = "8.4.7"
 
 import importlib
 import os

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/cfg/__init__.py

@@ -401,16 +401,16 @@ def get_save_dir(args: SimpleNamespace, name: str | None = None) -> Path:
         >>> args = SimpleNamespace(project="my_project", task="detect", mode="train", exist_ok=True)
         >>> save_dir = get_save_dir(args)
         >>> print(save_dir)
-        my_project/detect/train
+        runs/detect/my_project/train
     """
     if getattr(args, "save_dir", None):
         save_dir = args.save_dir
     else:
         from ultralytics.utils.files import increment_path
 
-        runs = (ROOT.parent / "tests/tmp/runs" if TESTS_RUNNING else RUNS_DIR) / args.task
-        nested = args.project and len(Path(args.project).parts) > 1  # e.g. "user/project" or "org\repo"
-        project = runs / args.project if nested else args.project or runs
+        project = args.project or ""
+        if not Path(project).is_absolute():
+            project = (ROOT.parent / "tests/tmp/runs" if TESTS_RUNNING else RUNS_DIR) / args.task / project
         name = name or args.name or f"{args.mode}"
         save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in {-1, 0} else True)
 

dgenerate_ultralytics_headless-8.4.7/ultralytics/cfg/datasets/coco12-formats.yaml

@@ -0,0 +1,101 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO12-Formats dataset (12 images testing all supported image formats) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/coco12-formats/
+# Example usage: yolo train data=coco12-formats.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco12-formats ← downloads here (1 MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: coco12-formats # dataset root dir
+train: images/train # train images (relative to 'path') 6 images
+val: images/val # val images (relative to 'path') 6 images
+test: # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco12-formats.zip

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/cfg/default.yaml

@@ -36,7 +36,7 @@ amp: True # (bool) Automatic Mixed Precision (AMP) training; True runs AMP capab
 fraction: 1.0 # (float) fraction of training dataset to use (1.0 = all)
 profile: False # (bool) profile ONNX/TensorRT speeds during training for loggers
 freeze: # (int | list, optional) freeze first N layers (int) or specific layer indices (list)
-multi_scale: 0.0 # (float) multiscale training by varying image size
+multi_scale: 0.0 # (float) multi-scale range as a fraction of imgsz; sizes are rounded to stride multiples
 compile: False # (bool | str) enable torch.compile() backend='inductor'; True="default", False=off, or "default|reduce-overhead|max-autotune-no-cudagraphs"
 
 # Segmentation

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/data/augment.py

@@ -2066,7 +2066,15 @@ class Format:
                 if self.mask_overlap:
                     sem_masks = cls_tensor[masks[0].long() - 1]  # (H, W) from (1, H, W) instance indices
                 else:
+                    # Create sem_masks consistent with mask_overlap=True
                     sem_masks = (masks * cls_tensor[:, None, None]).max(0).values  # (H, W) from (N, H, W) binary
+                    overlap = masks.sum(dim=0) > 1  # (H, W)
+                    if overlap.any():
+                        weights = masks.sum(axis=(1, 2))
+                        weighted_masks = masks * weights[:, None, None]  # (N, H, W)
+                        weighted_masks[masks == 0] = weights.max() + 1  # handle background
+                        smallest_idx = weighted_masks.argmin(dim=0)  # (H, W)
+                        sem_masks[overlap] = cls_tensor[smallest_idx[overlap]]
             else:
                 masks = torch.zeros(
                     1 if self.mask_overlap else nl, img.shape[0] // self.mask_ratio, img.shape[1] // self.mask_ratio

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/data/converter.py

@@ -838,14 +838,19 @@ async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Pat
             if http_url := record.get("url"):
                 if not image_path.exists():
                     image_path.parent.mkdir(parents=True, exist_ok=True)
-                    try:
-                        async with session.get(http_url, timeout=aiohttp.ClientTimeout(total=30)) as response:
-                            response.raise_for_status()
-                            image_path.write_bytes(await response.read())
-                        return True
-                    except Exception as e:
-                        LOGGER.warning(f"Failed to download {http_url}: {e}")
-                        return False
+                    # Retry with exponential backoff (3 attempts: 0s, 2s, 4s delays)
+                    for attempt in range(3):
+                        try:
+                            async with session.get(http_url, timeout=aiohttp.ClientTimeout(total=30)) as response:
+                                response.raise_for_status()
+                                image_path.write_bytes(await response.read())
+                            return True
+                        except Exception as e:
+                            if attempt < 2:  # Don't sleep after last attempt
+                                await asyncio.sleep(2**attempt)  # 1s, 2s backoff
+                            else:
+                                LOGGER.warning(f"Failed to download {http_url} after 3 attempts: {e}")
+                                return False
             return True
 
     # Process all images with async downloads (limit connections for small datasets)
@@ -861,9 +866,16 @@ async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Pat
             pbar.update(1)
             return result
 
-        await asyncio.gather(*[tracked_process(record) for record in image_records])
+        results = await asyncio.gather(*[tracked_process(record) for record in image_records])
         pbar.close()
 
+    # Validate images were downloaded successfully
+    success_count = sum(1 for r in results if r)
+    if success_count == 0:
+        raise RuntimeError(f"Failed to download any images from {ndjson_path}. Check network connection and URLs.")
+    if success_count < len(image_records):
+        LOGGER.warning(f"Downloaded {success_count}/{len(image_records)} images from {ndjson_path}")
+
     if is_classification:
         # Classification: return dataset directory (check_cls_dataset expects a directory path)
         return dataset_dir

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/data/utils.py

@@ -37,8 +37,8 @@ from ultralytics.utils.downloads import download, safe_download, unzip_file
 from ultralytics.utils.ops import segments2boxes
 
 HELP_URL = "See https://docs.ultralytics.com/datasets for dataset formatting guidance."
-IMG_FORMATS = {"bmp", "dng", "jpeg", "jpg", "mpo", "png", "tif", "tiff", "webp", "pfm", "heic"}  # image suffixes
-VID_FORMATS = {"asf", "avi", "gif", "m4v", "mkv", "mov", "mp4", "mpeg", "mpg", "ts", "wmv", "webm"}  # video suffixes
+IMG_FORMATS = {"avif", "bmp", "dng", "heic", "jp2", "jpeg", "jpeg2000", "jpg", "mpo", "png", "tif", "tiff", "webp"}
+VID_FORMATS = {"asf", "avi", "gif", "m4v", "mkv", "mov", "mp4", "mpeg", "mpg", "ts", "wmv", "webm"}  # videos
 FORMATS_HELP_MSG = f"Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}"
 
 

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/engine/trainer.py

@@ -981,11 +981,13 @@ class BaseTrainer:
                 "Request support for addition optimizers at https://github.com/ultralytics/ultralytics."
             )
 
+        num_params = [len(g[0]), len(g[1]), len(g[2])]  # number of param groups
         g[2] = {"params": g[2], **optim_args, "param_group": "bias"}
         g[0] = {"params": g[0], **optim_args, "weight_decay": decay, "param_group": "weight"}
         g[1] = {"params": g[1], **optim_args, "weight_decay": 0.0, "param_group": "bn"}
         muon, sgd = (0.1, 1.0) if iterations > 10000 else (0.5, 0.5)  # scale factor for MuSGD
         if use_muon:
+            num_params[0] = len(g[3])  # update number of params
             g[3] = {"params": g[3], **optim_args, "weight_decay": decay, "use_muon": True, "param_group": "muon"}
             import re
 
@@ -1002,6 +1004,6 @@ class BaseTrainer:
 
         LOGGER.info(
             f"{colorstr('optimizer:')} {type(optimizer).__name__}(lr={lr}, momentum={momentum}) with parameter groups "
-            f"{len(g[1]['params'])} weight(decay=0.0), {len(g[0]['params']) if len(g[0]) else len(g[3]['params'])} weight(decay={decay}), {len(g[2]['params'])} bias(decay=0.0)"
+            f"{num_params[1]} weight(decay=0.0), {num_params[0]} weight(decay={decay}), {num_params[2]} bias(decay=0.0)"
         )
         return optimizer

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/models/yolo/detect/train.py

@@ -117,11 +117,13 @@ class DetectionTrainer(BaseTrainer):
             if isinstance(v, torch.Tensor):
                 batch[k] = v.to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = batch["img"].float() / 255
-        multi_scale = self.args.multi_scale
-        if random.random() < multi_scale:
+        if self.args.multi_scale > 0.0:
             imgs = batch["img"]
             sz = (
-                random.randrange(int(self.args.imgsz * 0.5), int(self.args.imgsz * 1 + self.stride))
+                random.randrange(
+                    int(self.args.imgsz * (1.0 - self.args.multi_scale)),
+                    int(self.args.imgsz * (1.0 + self.args.multi_scale) + self.stride),
+                )
                 // self.stride
                 * self.stride
             )  # size

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/trackers/byte_tracker.py

@@ -270,9 +270,9 @@ class BYTETracker:
             args (Namespace): Command-line arguments containing tracking parameters.
             frame_rate (int): Frame rate of the video sequence.
         """
-        self.tracked_stracks = []  # type: list[STrack]
-        self.lost_stracks = []  # type: list[STrack]
-        self.removed_stracks = []  # type: list[STrack]
+        self.tracked_stracks: list[STrack] = []
+        self.lost_stracks: list[STrack] = []
+        self.removed_stracks: list[STrack] = []
 
         self.frame_id = 0
         self.args = args
@@ -304,7 +304,7 @@ class BYTETracker:
         detections = self.init_track(results, feats_keep)
         # Add newly detected tracklets to tracked_stracks
         unconfirmed = []
-        tracked_stracks = []  # type: list[STrack]
+        tracked_stracks: list[STrack] = []
         for track in self.tracked_stracks:
             if not track.is_activated:
                 unconfirmed.append(track)
@@ -423,9 +423,9 @@ class BYTETracker:
 
     def reset(self):
         """Reset the tracker by clearing all tracked, lost, and removed tracks and reinitializing the Kalman filter."""
-        self.tracked_stracks = []  # type: list[STrack]
-        self.lost_stracks = []  # type: list[STrack]
-        self.removed_stracks = []  # type: list[STrack]
+        self.tracked_stracks: list[STrack] = []
+        self.lost_stracks: list[STrack] = []
+        self.removed_stracks: list[STrack] = []
         self.frame_id = 0
         self.kalman_filter = self.get_kalmanfilter()
         self.reset_id()

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/utils/callbacks/platform.py

@@ -89,7 +89,8 @@ def resolve_platform_uri(uri, hard=True):
         raise ValueError(f"Invalid platform URI: {uri}. Use ul://user/datasets/name or ul://user/project/model")
 
     try:
-        r = requests.head(url, headers=headers, allow_redirects=False, timeout=30)
+        timeout = 3600 if "/datasets/" in url else 90  # NDJSON generation can be slow for large datasets
+        r = requests.head(url, headers=headers, allow_redirects=False, timeout=timeout)
 
         # Handle redirect responses (301, 302, 303, 307, 308)
         if 300 <= r.status_code < 400 and "location" in r.headers:

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/utils/callbacks/wb.py

@@ -128,10 +128,15 @@ def _log_plots(plots, step):
 def on_pretrain_routine_start(trainer):
     """Initialize and start wandb project if module is present."""
     if not wb.run:
+        from datetime import datetime
+
+        name = str(trainer.args.name).replace("/", "-").replace(" ", "_")
         wb.init(
             project=str(trainer.args.project).replace("/", "-") if trainer.args.project else "Ultralytics",
-            name=str(trainer.args.name).replace("/", "-"),
+            name=name,
             config=vars(trainer.args),
+            id=f"{name}_{datetime.now().strftime('%Y%m%d_%H%M%S')}",  # add unique id
+            dir=str(trainer.save_dir),
         )
 
 

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/utils/dist.py

@@ -49,6 +49,7 @@ def generate_ddp_file(trainer):
 
     content = f"""
 # Ultralytics Multi-GPU training temp file (should be automatically deleted after use)
+from pathlib import Path, PosixPath  # For model arguments stored as Path instead of str
 overrides = {vars(trainer.args)}
 
 if __name__ == "__main__":

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/utils/loss.py

@@ -512,9 +512,19 @@ class v8SegmentationLoss(v8DetectionLoss):
             )
             if pred_semseg is not None:
                 sem_masks = batch["sem_masks"].to(self.device)  # NxHxW
-                mask_zero = sem_masks == 0  # NxHxW
                 sem_masks = F.one_hot(sem_masks.long(), num_classes=self.nc).permute(0, 3, 1, 2).float()  # NxCxHxW
-                sem_masks[mask_zero.unsqueeze(1).expand_as(sem_masks)] = 0
+
+                if self.overlap:
+                    mask_zero = masks == 0  # NxHxW
+                    sem_masks[mask_zero.unsqueeze(1).expand_as(sem_masks)] = 0
+                else:
+                    batch_idx = batch["batch_idx"].view(-1)  # [total_instances]
+                    for i in range(batch_size):
+                        instance_mask_i = masks[batch_idx == i]  # [num_instances_i, H, W]
+                        if len(instance_mask_i) == 0:
+                            continue
+                        sem_masks[i, :, instance_mask_i.sum(dim=0) == 0] = 0
+
                 loss[4] = self.bcedice_loss(pred_semseg, sem_masks)
                 loss[4] *= self.hyp.box  # seg gain
 
@@ -798,7 +808,7 @@ class PoseLoss26(v8PoseLoss):
         loss[0], loss[3], loss[4] = det_loss[0], det_loss[1], det_loss[2]
 
         batch_size = pred_kpts.shape[0]
-        imgsz = torch.tensor(batch["resized_shape"][0], device=self.device, dtype=pred_kpts.dtype)  # image size (h,w)
+        imgsz = torch.tensor(preds["feats"][0].shape[2:], device=self.device, dtype=pred_kpts.dtype) * self.stride[0]
 
         pred_kpts = pred_kpts.view(batch_size, -1, *self.kpt_shape)  # (b, h*w, 17, 3)
 
@@ -992,7 +1002,7 @@ class v8OBBLoss(v8DetectionLoss):
         batch_size = pred_angle.shape[0]  # batch size, number of masks, mask height, mask width
 
         dtype = pred_scores.dtype
-        imgsz = torch.tensor(batch["resized_shape"][0], device=self.device, dtype=dtype)  # image size (h,w)
+        imgsz = torch.tensor(preds["feats"][0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]
 
         # targets
         try:

{dgenerate_ultralytics_headless-8.4.5 → dgenerate_ultralytics_headless-8.4.7}/ultralytics/utils/patches.py

@@ -40,9 +40,51 @@ def imread(filename: str, flags: int = cv2.IMREAD_COLOR) -> np.ndarray | None:
         return None
     else:
         im = cv2.imdecode(file_bytes, flags)
+        # Fallback for formats OpenCV imdecode may not support (AVIF, HEIC)
+        if im is None and filename.lower().endswith((".avif", ".heic")):
+            im = _imread_pil(filename, flags)
         return im[..., None] if im is not None and im.ndim == 2 else im  # Always ensure 3 dimensions
 
 
+_pil_plugins_registered = False
+
+
+def _imread_pil(filename: str, flags: int = cv2.IMREAD_COLOR) -> np.ndarray | None:
+    """Read an image using PIL as fallback for formats not supported by OpenCV.
+
+    Args:
+        filename (str): Path to the file to read.
+        flags (int, optional): OpenCV imread flags (used to determine grayscale conversion).
+
+    Returns:
+        (np.ndarray | None): The read image array in BGR format, or None if reading fails.
+    """
+    global _pil_plugins_registered
+    try:
+        from PIL import Image
+
+        # Register HEIF/AVIF plugins once
+        if not _pil_plugins_registered:
+            try:
+                import pillow_heif
+
+                pillow_heif.register_heif_opener()
+            except ImportError:
+                pass
+            try:
+                import pillow_avif  # noqa: F401
+            except ImportError:
+                pass
+            _pil_plugins_registered = True
+
+        with Image.open(filename) as img:
+            if flags == cv2.IMREAD_GRAYSCALE:
+                return np.asarray(img.convert("L"))
+            return cv2.cvtColor(np.asarray(img.convert("RGB")), cv2.COLOR_RGB2BGR)
+    except Exception:
+        return None
+
+
 def imwrite(filename: str, img: np.ndarray, params: list[int] | None = None) -> bool:
     """Write an image to a file with multilanguage filename support.