dgenerate-ultralytics-headless 8.3.134__py3-none-any.whl

ultralytics/data/scripts/download_weights.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Download latest models from https://github.com/ultralytics/assets/releases
+# Example usage: bash ultralytics/data/scripts/download_weights.sh
+# parent
+# └── weights
+#     ├── yolov8n.pt  ← downloads here
+#     ├── yolov8s.pt
+#     └── ...
+
+python << EOF
+from ultralytics.utils.downloads import attempt_download_asset
+
+assets = [f"yolov8{size}{suffix}.pt" for size in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose")]
+for x in assets:
+    attempt_download_asset(f"weights/{x}")
+EOF

ultralytics/data/scripts/get_coco.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Download COCO 2017 dataset https://cocodataset.org
+# Example usage: bash data/scripts/get_coco.sh
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco  ← downloads here
+
+# Arguments (optional) Usage: bash data/scripts/get_coco.sh --train --val --test --segments
+if [ "$#" -gt 0 ]; then
+  for opt in "$@"; do
+    case "${opt}" in
+      --train) train=true ;;
+      --val) val=true ;;
+      --test) test=true ;;
+      --segments) segments=true ;;
+      --sama) sama=true ;;
+    esac
+  done
+else
+  train=true
+  val=true
+  test=false
+  segments=false
+  sama=false
+fi
+
+# Download/unzip labels
+d='../datasets' # unzip directory
+url=https://github.com/ultralytics/assets/releases/download/v0.0.0/
+if [ "$segments" == "true" ]; then
+  f='coco2017labels-segments.zip' # 169 MB
+elif [ "$sama" == "true" ]; then
+  f='coco2017labels-segments-sama.zip' # 199 MB https://www.sama.com/sama-coco-dataset/
+else
+  f='coco2017labels.zip' # 46 MB
+fi
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &
+
+# Download/unzip images
+d='../datasets/coco/images' # unzip directory
+url=http://images.cocodataset.org/zips/
+if [ "$train" == "true" ]; then
+  f='train2017.zip' # 19G, 118k images
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &
+fi
+if [ "$val" == "true" ]; then
+  f='val2017.zip' # 1G, 5k images
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &
+fi
+if [ "$test" == "true" ]; then
+  f='test2017.zip' # 7G, 41k images (optional)
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &
+fi
+wait # finish background tasks

ultralytics/data/scripts/get_coco128.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Download COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
+# Example usage: bash data/scripts/get_coco128.sh
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco128  ← downloads here
+
+# Download/unzip images and labels
+d='../datasets' # unzip directory
+url=https://github.com/ultralytics/assets/releases/download/v0.0.0/
+f='coco128.zip' # or 'coco128-segments.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &
+
+wait # finish background tasks

ultralytics/data/scripts/get_imagenet.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Download ILSVRC2012 ImageNet dataset https://image-net.org
+# Example usage: bash data/scripts/get_imagenet.sh
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── imagenet  ← downloads here
+
+# Arguments (optional) Usage: bash data/scripts/get_imagenet.sh --train --val
+if [ "$#" -gt 0 ]; then
+  for opt in "$@"; do
+    case "${opt}" in
+      --train) train=true ;;
+      --val) val=true ;;
+    esac
+  done
+else
+  train=true
+  val=true
+fi
+
+# Make dir
+d='../datasets/imagenet' # unzip directory
+mkdir -p $d && cd $d
+
+# Download/unzip train
+if [ "$train" == "true" ]; then
+  wget https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_train.tar # download 138G, 1281167 images
+  mkdir train && mv ILSVRC2012_img_train.tar train/ && cd train
+  tar -xf ILSVRC2012_img_train.tar && rm -f ILSVRC2012_img_train.tar
+  find . -name "*.tar" | while read NAME; do
+    mkdir -p "${NAME%.tar}"
+    tar -xf "${NAME}" -C "${NAME%.tar}"
+    rm -f "${NAME}"
+  done
+  cd ..
+fi
+
+# Download/unzip val
+if [ "$val" == "true" ]; then
+  wget https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_val.tar # download 6.3G, 50000 images
+  mkdir val && mv ILSVRC2012_img_val.tar val/ && cd val && tar -xf ILSVRC2012_img_val.tar
+  wget -qO- https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh | bash # move into subdirs
+fi
+
+# Delete corrupted image (optional: PNG under JPEG name that may cause dataloaders to fail)
+# rm train/n04266014/n04266014_10835.JPEG
+
+# TFRecords (optional)
+# wget https://raw.githubusercontent.com/tensorflow/models/master/research/slim/datasets/imagenet_lsvrc_2015_synsets.txt

ultralytics/data/split.py

@@ -0,0 +1,125 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import random
+import shutil
+from pathlib import Path
+
+from ultralytics.data.utils import IMG_FORMATS, img2label_paths
+from ultralytics.utils import DATASETS_DIR, LOGGER, TQDM
+
+
+def split_classify_dataset(source_dir, train_ratio=0.8):
+    """
+    Split dataset into train and val directories in a new directory.
+
+    Creates a new directory '{source_dir}_split' with train/val subdirectories, preserving the original class
+    structure with an 80/20 split by default.
+
+    Directory structure:
+        Before:
+            caltech/
+            ├── class1/
+            │   ├── img1.jpg
+            │   ├── img2.jpg
+            │   └── ...
+            ├── class2/
+            │   ├── img1.jpg
+            │   └── ...
+            └── ...
+
+        After:
+            caltech_split/
+            ├── train/
+            │   ├── class1/
+            │   │   ├── img1.jpg
+            │   │   └── ...
+            │   ├── class2/
+            │   │   ├── img1.jpg
+            │   │   └── ...
+            │   └── ...
+            └── val/
+                ├── class1/
+                │   ├── img2.jpg
+                │   └── ...
+                ├── class2/
+                │   └── ...
+                └── ...
+
+    Args:
+        source_dir (str | Path): Path to Caltech dataset root directory.
+        train_ratio (float): Ratio for train split, between 0 and 1.
+
+    Examples:
+        >>> # Split dataset with default 80/20 ratio
+        >>> split_classify_dataset("path/to/caltech")
+        >>> # Split with custom ratio
+        >>> split_classify_dataset("path/to/caltech", 0.75)
+    """
+    source_path = Path(source_dir)
+    split_path = Path(f"{source_path}_split")
+    train_path, val_path = split_path / "train", split_path / "val"
+
+    # Create directory structure
+    split_path.mkdir(exist_ok=True)
+    train_path.mkdir(exist_ok=True)
+    val_path.mkdir(exist_ok=True)
+
+    # Process class directories
+    class_dirs = [d for d in source_path.iterdir() if d.is_dir()]
+    total_images = sum(len(list(d.glob("*.*"))) for d in class_dirs)
+    stats = f"{len(class_dirs)} classes, {total_images} images"
+    LOGGER.info(f"Splitting {source_path} ({stats}) into {train_ratio:.0%} train, {1 - train_ratio:.0%} val...")
+
+    for class_dir in class_dirs:
+        # Create class directories
+        (train_path / class_dir.name).mkdir(exist_ok=True)
+        (val_path / class_dir.name).mkdir(exist_ok=True)
+
+        # Split and copy files
+        image_files = list(class_dir.glob("*.*"))
+        random.shuffle(image_files)
+        split_idx = int(len(image_files) * train_ratio)
+
+        for img in image_files[:split_idx]:
+            shutil.copy2(img, train_path / class_dir.name / img.name)
+
+        for img in image_files[split_idx:]:
+            shutil.copy2(img, val_path / class_dir.name / img.name)
+
+    LOGGER.info(f"Split complete in {split_path} ✅")
+    return split_path
+
+
+def autosplit(path=DATASETS_DIR / "coco8/images", weights=(0.9, 0.1, 0.0), annotated_only=False):
+    """
+    Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
+
+    Args:
+        path (Path, optional): Path to images directory.
+        weights (list | tuple, optional): Train, validation, and test split fractions.
+        annotated_only (bool, optional): If True, only images with an associated txt file are used.
+
+    Examples:
+        >>> from ultralytics.data.split import autosplit
+        >>> autosplit()
+    """
+    path = Path(path)  # images dir
+    files = sorted(x for x in path.rglob("*.*") if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
+    n = len(files)  # number of files
+    random.seed(0)  # for reproducibility
+    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+
+    txt = ["autosplit_train.txt", "autosplit_val.txt", "autosplit_test.txt"]  # 3 txt files
+    for x in txt:
+        if (path.parent / x).exists():
+            (path.parent / x).unlink()  # remove existing
+
+    LOGGER.info(f"Autosplitting images from {path}" + ", using *.txt labeled images only" * annotated_only)
+    for i, img in TQDM(zip(indices, files), total=n):
+        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
+            with open(path.parent / txt[i], "a", encoding="utf-8") as f:
+                f.write(f"./{img.relative_to(path.parent).as_posix()}" + "\n")  # add image to txt file
+
+
+if __name__ == "__main__":
+    split_classify_dataset("../datasets/caltech101")

ultralytics/data/split_dota.py

@@ -0,0 +1,325 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import itertools
+from glob import glob
+from math import ceil
+from pathlib import Path
+
+import cv2
+import numpy as np
+from PIL import Image
+
+from ultralytics.data.utils import exif_size, img2label_paths
+from ultralytics.utils import TQDM
+from ultralytics.utils.checks import check_requirements
+
+
+def bbox_iof(polygon1, bbox2, eps=1e-6):
+    """
+    Calculate Intersection over Foreground (IoF) between polygons and bounding boxes.
+
+    Args:
+        polygon1 (np.ndarray): Polygon coordinates with shape (n, 8).
+        bbox2 (np.ndarray): Bounding boxes with shape (n, 4).
+        eps (float, optional): Small value to prevent division by zero.
+
+    Returns:
+        (np.ndarray): IoF scores with shape (n, 1) or (n, m) if bbox2 is (m, 4).
+
+    Notes:
+        Polygon format: [x1, y1, x2, y2, x3, y3, x4, y4].
+        Bounding box format: [x_min, y_min, x_max, y_max].
+    """
+    check_requirements("shapely>=2.0.0")
+    from shapely.geometry import Polygon
+
+    polygon1 = polygon1.reshape(-1, 4, 2)
+    lt_point = np.min(polygon1, axis=-2)  # left-top
+    rb_point = np.max(polygon1, axis=-2)  # right-bottom
+    bbox1 = np.concatenate([lt_point, rb_point], axis=-1)
+
+    lt = np.maximum(bbox1[:, None, :2], bbox2[..., :2])
+    rb = np.minimum(bbox1[:, None, 2:], bbox2[..., 2:])
+    wh = np.clip(rb - lt, 0, np.inf)
+    h_overlaps = wh[..., 0] * wh[..., 1]
+
+    left, top, right, bottom = (bbox2[..., i] for i in range(4))
+    polygon2 = np.stack([left, top, right, top, right, bottom, left, bottom], axis=-1).reshape(-1, 4, 2)
+
+    sg_polys1 = [Polygon(p) for p in polygon1]
+    sg_polys2 = [Polygon(p) for p in polygon2]
+    overlaps = np.zeros(h_overlaps.shape)
+    for p in zip(*np.nonzero(h_overlaps)):
+        overlaps[p] = sg_polys1[p[0]].intersection(sg_polys2[p[-1]]).area
+    unions = np.array([p.area for p in sg_polys1], dtype=np.float32)
+    unions = unions[..., None]
+
+    unions = np.clip(unions, eps, np.inf)
+    outputs = overlaps / unions
+    if outputs.ndim == 1:
+        outputs = outputs[..., None]
+    return outputs
+
+
+def load_yolo_dota(data_root, split="train"):
+    """
+    Load DOTA dataset.
+
+    Args:
+        data_root (str): Data root directory.
+        split (str): The split data set, could be `train` or `val`.
+
+    Returns:
+        (List[Dict]): List of annotation dictionaries containing image information.
+
+    Notes:
+        The directory structure assumed for the DOTA dataset:
+            - data_root
+                - images
+                    - train
+                    - val
+                - labels
+                    - train
+                    - val
+    """
+    assert split in {"train", "val"}, f"Split must be 'train' or 'val', not {split}."
+    im_dir = Path(data_root) / "images" / split
+    assert im_dir.exists(), f"Can't find {im_dir}, please check your data root."
+    im_files = glob(str(Path(data_root) / "images" / split / "*"))
+    lb_files = img2label_paths(im_files)
+    annos = []
+    for im_file, lb_file in zip(im_files, lb_files):
+        w, h = exif_size(Image.open(im_file))
+        with open(lb_file, encoding="utf-8") as f:
+            lb = [x.split() for x in f.read().strip().splitlines() if len(x)]
+            lb = np.array(lb, dtype=np.float32)
+        annos.append(dict(ori_size=(h, w), label=lb, filepath=im_file))
+    return annos
+
+
+def get_windows(im_size, crop_sizes=(1024,), gaps=(200,), im_rate_thr=0.6, eps=0.01):
+    """
+    Get the coordinates of windows.
+
+    Args:
+        im_size (tuple): Original image size, (h, w).
+        crop_sizes (List[int]): Crop size of windows.
+        gaps (List[int]): Gap between crops.
+        im_rate_thr (float): Threshold of windows areas divided by image areas.
+        eps (float): Epsilon value for math operations.
+
+    Returns:
+        (np.ndarray): Array of window coordinates with shape (n, 4) where each row is [x_start, y_start, x_stop, y_stop].
+    """
+    h, w = im_size
+    windows = []
+    for crop_size, gap in zip(crop_sizes, gaps):
+        assert crop_size > gap, f"invalid crop_size gap pair [{crop_size} {gap}]"
+        step = crop_size - gap
+
+        xn = 1 if w <= crop_size else ceil((w - crop_size) / step + 1)
+        xs = [step * i for i in range(xn)]
+        if len(xs) > 1 and xs[-1] + crop_size > w:
+            xs[-1] = w - crop_size
+
+        yn = 1 if h <= crop_size else ceil((h - crop_size) / step + 1)
+        ys = [step * i for i in range(yn)]
+        if len(ys) > 1 and ys[-1] + crop_size > h:
+            ys[-1] = h - crop_size
+
+        start = np.array(list(itertools.product(xs, ys)), dtype=np.int64)
+        stop = start + crop_size
+        windows.append(np.concatenate([start, stop], axis=1))
+    windows = np.concatenate(windows, axis=0)
+
+    im_in_wins = windows.copy()
+    im_in_wins[:, 0::2] = np.clip(im_in_wins[:, 0::2], 0, w)
+    im_in_wins[:, 1::2] = np.clip(im_in_wins[:, 1::2], 0, h)
+    im_areas = (im_in_wins[:, 2] - im_in_wins[:, 0]) * (im_in_wins[:, 3] - im_in_wins[:, 1])
+    win_areas = (windows[:, 2] - windows[:, 0]) * (windows[:, 3] - windows[:, 1])
+    im_rates = im_areas / win_areas
+    if not (im_rates > im_rate_thr).any():
+        max_rate = im_rates.max()
+        im_rates[abs(im_rates - max_rate) < eps] = 1
+    return windows[im_rates > im_rate_thr]
+
+
+def get_window_obj(anno, windows, iof_thr=0.7):
+    """Get objects for each window."""
+    h, w = anno["ori_size"]
+    label = anno["label"]
+    if len(label):
+        label[:, 1::2] *= w
+        label[:, 2::2] *= h
+        iofs = bbox_iof(label[:, 1:], windows)
+        # Unnormalized and misaligned coordinates
+        return [(label[iofs[:, i] >= iof_thr]) for i in range(len(windows))]  # window_anns
+    else:
+        return [np.zeros((0, 9), dtype=np.float32) for _ in range(len(windows))]  # window_anns
+
+
+def crop_and_save(anno, windows, window_objs, im_dir, lb_dir, allow_background_images=True):
+    """
+    Crop images and save new labels.
+
+    Args:
+        anno (dict): Annotation dict, including `filepath`, `label`, `ori_size` as its keys.
+        windows (np.ndarray): Array of windows coordinates with shape (n, 4).
+        window_objs (list): A list of labels inside each window.
+        im_dir (str): The output directory path of images.
+        lb_dir (str): The output directory path of labels.
+        allow_background_images (bool): Whether to include background images without labels.
+
+    Notes:
+        The directory structure assumed for the DOTA dataset:
+            - data_root
+                - images
+                    - train
+                    - val
+                - labels
+                    - train
+                    - val
+    """
+    im = cv2.imread(anno["filepath"])
+    name = Path(anno["filepath"]).stem
+    for i, window in enumerate(windows):
+        x_start, y_start, x_stop, y_stop = window.tolist()
+        new_name = f"{name}__{x_stop - x_start}__{x_start}___{y_start}"
+        patch_im = im[y_start:y_stop, x_start:x_stop]
+        ph, pw = patch_im.shape[:2]
+
+        label = window_objs[i]
+        if len(label) or allow_background_images:
+            cv2.imwrite(str(Path(im_dir) / f"{new_name}.jpg"), patch_im)
+        if len(label):
+            label[:, 1::2] -= x_start
+            label[:, 2::2] -= y_start
+            label[:, 1::2] /= pw
+            label[:, 2::2] /= ph
+
+            with open(Path(lb_dir) / f"{new_name}.txt", "w", encoding="utf-8") as f:
+                for lb in label:
+                    formatted_coords = [f"{coord:.6g}" for coord in lb[1:]]
+                    f.write(f"{int(lb[0])} {' '.join(formatted_coords)}\n")
+
+
+def split_images_and_labels(data_root, save_dir, split="train", crop_sizes=(1024,), gaps=(200,)):
+    """
+    Split both images and labels.
+
+    Args:
+        data_root (str): Root directory of the dataset.
+        save_dir (str): Directory to save the split dataset.
+        split (str): The split data set, could be `train` or `val`.
+        crop_sizes (tuple): Tuple of crop sizes.
+        gaps (tuple): Tuple of gaps between crops.
+
+    Notes:
+        The directory structure assumed for the DOTA dataset:
+            - data_root
+                - images
+                    - split
+                - labels
+                    - split
+        and the output directory structure is:
+            - save_dir
+                - images
+                    - split
+                - labels
+                    - split
+    """
+    im_dir = Path(save_dir) / "images" / split
+    im_dir.mkdir(parents=True, exist_ok=True)
+    lb_dir = Path(save_dir) / "labels" / split
+    lb_dir.mkdir(parents=True, exist_ok=True)
+
+    annos = load_yolo_dota(data_root, split=split)
+    for anno in TQDM(annos, total=len(annos), desc=split):
+        windows = get_windows(anno["ori_size"], crop_sizes, gaps)
+        window_objs = get_window_obj(anno, windows)
+        crop_and_save(anno, windows, window_objs, str(im_dir), str(lb_dir))
+
+
+def split_trainval(data_root, save_dir, crop_size=1024, gap=200, rates=(1.0,)):
+    """
+    Split train and val set of DOTA.
+
+    Args:
+        data_root (str): Root directory of the dataset.
+        save_dir (str): Directory to save the split dataset.
+        crop_size (int): Base crop size.
+        gap (int): Base gap between crops.
+        rates (tuple): Scaling rates for crop_size and gap.
+
+    Notes:
+        The directory structure assumed for the DOTA dataset:
+            - data_root
+                - images
+                    - train
+                    - val
+                - labels
+                    - train
+                    - val
+        and the output directory structure is:
+            - save_dir
+                - images
+                    - train
+                    - val
+                - labels
+                    - train
+                    - val
+    """
+    crop_sizes, gaps = [], []
+    for r in rates:
+        crop_sizes.append(int(crop_size / r))
+        gaps.append(int(gap / r))
+    for split in ["train", "val"]:
+        split_images_and_labels(data_root, save_dir, split, crop_sizes, gaps)
+
+
+def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=(1.0,)):
+    """
+    Split test set of DOTA, labels are not included within this set.
+
+    Args:
+        data_root (str): Root directory of the dataset.
+        save_dir (str): Directory to save the split dataset.
+        crop_size (int): Base crop size.
+        gap (int): Base gap between crops.
+        rates (tuple): Scaling rates for crop_size and gap.
+
+    Notes:
+        The directory structure assumed for the DOTA dataset:
+            - data_root
+                - images
+                    - test
+        and the output directory structure is:
+            - save_dir
+                - images
+                    - test
+    """
+    crop_sizes, gaps = [], []
+    for r in rates:
+        crop_sizes.append(int(crop_size / r))
+        gaps.append(int(gap / r))
+    save_dir = Path(save_dir) / "images" / "test"
+    save_dir.mkdir(parents=True, exist_ok=True)
+
+    im_dir = Path(data_root) / "images" / "test"
+    assert im_dir.exists(), f"Can't find {im_dir}, please check your data root."
+    im_files = glob(str(im_dir / "*"))
+    for im_file in TQDM(im_files, total=len(im_files), desc="test"):
+        w, h = exif_size(Image.open(im_file))
+        windows = get_windows((h, w), crop_sizes=crop_sizes, gaps=gaps)
+        im = cv2.imread(im_file)
+        name = Path(im_file).stem
+        for window in windows:
+            x_start, y_start, x_stop, y_stop = window.tolist()
+            new_name = f"{name}__{x_stop - x_start}__{x_start}___{y_start}"
+            patch_im = im[y_start:y_stop, x_start:x_stop]
+            cv2.imwrite(str(save_dir / f"{new_name}.jpg"), patch_im)
+
+
+if __name__ == "__main__":
+    split_trainval(data_root="DOTAv2", save_dir="DOTAv2-split")
+    split_test(data_root="DOTAv2", save_dir="DOTAv2-split")