dgenerate-ultralytics-headless 8.3.181__tar.gz → 8.3.183__tar.gz

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.181
+Version: 8.3.183
 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>

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/dgenerate_ultralytics_headless.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.181
+Version: 8.3.183
 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>

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/dgenerate_ultralytics_headless.egg-info/SOURCES.txt

@@ -15,6 +15,7 @@ tests/test_integrations.py
 tests/test_python.py
 tests/test_solutions.py
 ultralytics/__init__.py
+ultralytics/py.typed
 ultralytics/../tests/__init__.py
 ultralytics/../tests/conftest.py
 ultralytics/../tests/test_cli.py

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/tests/test_cuda.py

@@ -67,7 +67,7 @@ def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
         half=half,
         batch=batch,
         simplify=simplify,
-        nms=nms,
+        nms=nms and task != "obb",  # disable NMS for OBB task for now on T4 instance
         device=DEVICES[0],
     )
     YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, device=DEVICES[0])  # exported model inference
@@ -163,7 +163,7 @@ def test_autobatch():
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(not DEVICES, reason="No CUDA devices available")
+@pytest.mark.skipif(True, reason="Skip for now since T4 instance does not support TensorRT > 10.0")
 def test_utils_benchmarks():
     """Profile YOLO models for performance benchmarks."""
     from ultralytics.utils.benchmarks import ProfileModels

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/tests/test_python.py

@@ -228,6 +228,15 @@ def test_train_scratch():
     model(SOURCE)
 
 
+@pytest.mark.skipif(not ONLINE, reason="environment is offline")
+def test_train_ndjson():
+    """Test training the YOLO model using NDJSON format dataset."""
+    model = YOLO(WEIGHTS_DIR / "yolo11n.pt")
+    model.train(
+        data="https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-ndjson.ndjson", epochs=1, imgsz=32
+    )
+
+
 @pytest.mark.parametrize("scls", [False, True])
 def test_train_pretrained(scls):
     """Test training of the YOLO model starting from a pre-trained checkpoint."""

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.181"
+__version__ = "8.3.183"
 
 import os
 

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/data/converter.py

@@ -1,5 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+import asyncio
 import json
 import random
 import shutil
@@ -12,7 +13,8 @@ import cv2
 import numpy as np
 from PIL import Image
 
-from ultralytics.utils import DATASETS_DIR, LOGGER, NUM_THREADS, TQDM
+from ultralytics.utils import DATASETS_DIR, LOGGER, NUM_THREADS, TQDM, YAML
+from ultralytics.utils.checks import check_file, check_requirements
 from ultralytics.utils.downloads import download, zip_directory
 from ultralytics.utils.files import increment_path
 
@@ -754,3 +756,112 @@ def convert_to_multispectral(path: Union[str, Path], n_channels: int = 10, repla
         multispectral = f(target_wavelengths)
         cv2.imwritemulti(str(output_path), np.clip(multispectral, 0, 255).astype(np.uint8).transpose(2, 0, 1))
         LOGGER.info(f"Converted {output_path}")
+
+
+async def convert_ndjson_to_yolo(ndjson_path: Union[str, Path], output_path: Optional[Union[str, Path]] = None) -> Path:
+    """
+    Convert NDJSON dataset format to Ultralytics YOLO11 dataset structure.
+
+    This function converts datasets stored in NDJSON (Newline Delimited JSON) format to the standard YOLO
+    format with separate directories for images and labels. It supports parallel processing for efficient
+    conversion of large datasets and can download images from URLs if they don't exist locally.
+
+    The NDJSON format consists of:
+    - First line: Dataset metadata with class names and configuration
+    - Subsequent lines: Individual image records with annotations and optional URLs
+
+    Args:
+        ndjson_path (Union[str, Path]): Path to the input NDJSON file containing dataset information.
+        output_path (Optional[Union[str, Path]], optional): Directory where the converted YOLO dataset
+            will be saved. If None, uses the parent directory of the NDJSON file. Defaults to None.
+
+    Returns:
+        (Path): Path to the generated data.yaml file that can be used for YOLO training.
+
+    Examples:
+        Convert a local NDJSON file:
+        >>> yaml_path = convert_ndjson_to_yolo("dataset.ndjson")
+        >>> print(f"Dataset converted to: {yaml_path}")
+
+        Convert with custom output directory:
+        >>> yaml_path = convert_ndjson_to_yolo("dataset.ndjson", output_path="./converted_datasets")
+
+        # Use with YOLO training
+        >>> from ultralytics import YOLO
+        >>> model = YOLO("yolo11n.pt")
+        >>> model.train(data="https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-ndjson.ndjson")
+    """
+    check_requirements("aiohttp")
+    import aiohttp
+
+    ndjson_path = Path(check_file(ndjson_path))
+    output_path = Path(output_path or DATASETS_DIR)
+    with open(ndjson_path) as f:
+        lines = [json.loads(line.strip()) for line in f if line.strip()]
+
+    dataset_record, image_records = lines[0], lines[1:]
+    dataset_dir = output_path / ndjson_path.stem
+    splits = {record["split"] for record in image_records}
+
+    # Create directories and prepare YAML structure
+    dataset_dir.mkdir(parents=True, exist_ok=True)
+    data_yaml = dict(dataset_record)
+    data_yaml["names"] = {int(k): v for k, v in dataset_record.get("class_names", {}).items()}
+
+    for split in sorted(splits):
+        (dataset_dir / "images" / split).mkdir(parents=True, exist_ok=True)
+        (dataset_dir / "labels" / split).mkdir(parents=True, exist_ok=True)
+        data_yaml[split] = f"images/{split}"
+
+    async def process_record(session, semaphore, record):
+        """Process single image record with async session."""
+        async with semaphore:
+            split, original_name = record["split"], record["file"]
+            label_path = dataset_dir / "labels" / split / f"{Path(original_name).stem}.txt"
+            image_path = dataset_dir / "images" / split / original_name
+
+            annotations = record.get("annotations", {})
+            lines_to_write = []
+            for key in annotations.keys():
+                lines_to_write = [" ".join(map(str, item)) for item in annotations[key]]
+                break
+            if "classification" in annotations:
+                lines_to_write = [str(cls) for cls in annotations["classification"]]
+
+            label_path.write_text("\n".join(lines_to_write) + "\n" if lines_to_write else "")
+
+            if http_url := record.get("url"):
+                if not image_path.exists():
+                    try:
+                        async with session.get(http_url, timeout=aiohttp.ClientTimeout(total=30)) as response:
+                            response.raise_for_status()
+                            with open(image_path, "wb") as f:
+                                async for chunk in response.content.iter_chunked(8192):
+                                    f.write(chunk)
+                        return True
+                    except Exception as e:
+                        LOGGER.warning(f"Failed to download {http_url}: {e}")
+                        return False
+            return True
+
+    # Process all images with async downloads
+    semaphore = asyncio.Semaphore(64)
+    async with aiohttp.ClientSession() as session:
+        pbar = TQDM(
+            total=len(image_records),
+            desc=f"Converting {ndjson_path.name} → {dataset_dir} ({len(image_records)} images)",
+        )
+
+        async def tracked_process(record):
+            result = await process_record(session, semaphore, record)
+            pbar.update(1)
+            return result
+
+        await asyncio.gather(*[tracked_process(record) for record in image_records])
+        pbar.close()
+
+    # Write data.yaml
+    yaml_path = dataset_dir / "data.yaml"
+    YAML.save(yaml_path, data_yaml)
+
+    return yaml_path

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/engine/trainer.py

@@ -598,6 +598,15 @@ class BaseTrainer:
         try:
             if self.args.task == "classify":
                 data = check_cls_dataset(self.args.data)
+            elif self.args.data.rsplit(".", 1)[-1] == "ndjson":
+                # Convert NDJSON to YOLO format
+                import asyncio
+
+                from ultralytics.data.converter import convert_ndjson_to_yolo
+
+                yaml_path = asyncio.run(convert_ndjson_to_yolo(self.args.data))
+                self.args.data = str(yaml_path)
+                data = check_det_dataset(self.args.data)
             elif self.args.data.rsplit(".", 1)[-1] in {"yaml", "yml"} or self.args.task in {
                 "detect",
                 "segment",

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/models/sam/modules/sam.py

@@ -1032,3 +1032,4 @@ class SAM2Model(torch.nn.Module):
         self.image_size = imgsz[0]
         self.sam_prompt_encoder.input_image_size = imgsz
         self.sam_prompt_encoder.image_embedding_size = [x // 16 for x in imgsz]  # fixed ViT patch size of 16
+        self.sam_image_embedding_size = self.image_size // self.backbone_stride  # update image embedding size

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/models/sam/predict.py

@@ -1283,6 +1283,7 @@ class SAM2VideoPredictor(SAM2Predictor):
             - If `batch` is greater than 1, the features are expanded to fit the batch size.
             - The method leverages the model's `_prepare_backbone_features` method to prepare the backbone features.
         """
+        self.model.set_imgsz(self.imgsz)
         backbone_out = self.model.forward_image(im)
         if batch > 1:  # expand features if there's more than one prompt
             for i, feat in enumerate(backbone_out["backbone_fpn"]):

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/models/yolo/yoloe/val.py

@@ -181,7 +181,7 @@ class YOLOEDetectValidator(DetectionValidator):
         else:
             if refer_data is not None:
                 assert load_vp, "Refer data is only used for visual prompt validation."
-            self.device = select_device(self.args.device)
+            self.device = select_device(self.args.device, verbose=False)
 
             if isinstance(model, (str, Path)):
                 from ultralytics.nn.tasks import attempt_load_weights

dgenerate_ultralytics_headless-8.3.183/ultralytics/py.typed

@@ -0,0 +1 @@
+partial

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.183}/ultralytics/utils/plotting.py

@@ -361,38 +361,46 @@ class Annotator:
                     lineType=cv2.LINE_AA,
                 )
 
-    def masks(self, masks, colors, im_gpu, alpha: float = 0.5, retina_masks: bool = False):
+    def masks(self, masks, colors, im_gpu: torch.Tensor = None, alpha: float = 0.5, retina_masks: bool = False):
         """
         Plot masks on image.
 
         Args:
-            masks (torch.Tensor): Predicted masks on cuda, shape: [n, h, w]
+            masks (torch.Tensor | np.ndarray): Predicted masks with shape: [n, h, w]
             colors (List[List[int]]): Colors for predicted masks, [[r, g, b] * n]
-            im_gpu (torch.Tensor): Image is in cuda, shape: [3, h, w], range: [0, 1]
+            im_gpu (torch.Tensor | None): Image is in cuda, shape: [3, h, w], range: [0, 1]
             alpha (float, optional): Mask transparency: 0.0 fully transparent, 1.0 opaque.
             retina_masks (bool, optional): Whether to use high resolution masks or not.
         """
         if self.pil:
             # Convert to numpy first
             self.im = np.asarray(self.im).copy()
-        if len(masks) == 0:
-            self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
-        if im_gpu.device != masks.device:
-            im_gpu = im_gpu.to(masks.device)
-        colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
-        colors = colors[:, None, None]  # shape(n,1,1,3)
-        masks = masks.unsqueeze(3)  # shape(n,h,w,1)
-        masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
-
-        inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
-        mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)
-
-        im_gpu = im_gpu.flip(dims=[0])  # flip channel
-        im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
-        im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
-        im_mask = im_gpu * 255
-        im_mask_np = im_mask.byte().cpu().numpy()
-        self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
+        if im_gpu is None:
+            assert isinstance(masks, np.ndarray), "`masks` must be a np.ndarray if `im_gpu` is not provided."
+            overlay = self.im.copy()
+            for i, mask in enumerate(masks):
+                overlay[mask.astype(bool)] = colors[i]
+            self.im = cv2.addWeighted(self.im, 1 - alpha, overlay, alpha, 0)
+        else:
+            assert isinstance(masks, torch.Tensor), "`masks` must be a torch.Tensor if `im_gpu` is provided."
+            if len(masks) == 0:
+                self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
+            if im_gpu.device != masks.device:
+                im_gpu = im_gpu.to(masks.device)
+            colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
+            colors = colors[:, None, None]  # shape(n,1,1,3)
+            masks = masks.unsqueeze(3)  # shape(n,h,w,1)
+            masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
+
+            inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
+            mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)
+
+            im_gpu = im_gpu.flip(dims=[0])  # flip channel
+            im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
+            im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
+            im_mask = im_gpu * 255
+            im_mask_np = im_mask.byte().cpu().numpy()
+            self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
         if self.pil:
             # Convert im back to PIL and update draw
             self.fromarray(self.im)