pip install -U albumentations opencv-python

>>> from datasets import load_dataset

>>> dataset = load_dataset("scene_parse_150", split="train")
>>> index = 10
>>> dataset[index]
{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=683x512 at 0x7FB37B0EC810>,
 'annotation': <PIL.PngImagePlugin.PngImageFile image mode=L size=683x512 at 0x7FB37B0EC9D0>,
 'scene_category': 927}

>>> dataset[index]["image"]

>>> dataset[index]["annotation"]

>>> import matplotlib.pyplot as plt

>>> def visualize_seg_mask(image: np.ndarray, mask: np.ndarray):
...    color_seg = np.zeros((mask.shape[0], mask.shape[1], 3), dtype=np.uint8)
...    palette = np.array(create_ade20k_label_colormap())
...    for label, color in enumerate(palette):
...        color_seg[mask == label, :] = color
...    color_seg = color_seg[..., ::-1]  # convert to BGR

...    img = np.array(image) * 0.5 + color_seg * 0.5  # plot the image with the segmentation map
...    img = img.astype(np.uint8)

...    plt.figure(figsize=(15, 10))
...    plt.imshow(img)
...    plt.axis("off")
...    plt.show()


>>> visualize_seg_mask(
...     np.array(dataset[index]["image"]),
...     np.array(dataset[index]["annotation"])
... )

>>> import albumentations

>>> transform = albumentations.Compose(
...     [
...         albumentations.Resize(256, 256),
...         albumentations.RandomBrightnessContrast(brightness_limit=0.3, contrast_limit=0.3, p=0.5),
...     ]
... )

>>> def transforms(examples):
...     transformed_images, transformed_masks = [], []
...
...     for image, seg_mask in zip(examples["image"], examples["annotation"]):
...         image, seg_mask = np.array(image), np.array(seg_mask)
...         transformed = transform(image=image, mask=seg_mask)
...         transformed_images.append(transformed["image"])
...         transformed_masks.append(transformed["mask"])
...
...     examples["pixel_values"] = transformed_images
...     examples["label"] = transformed_masks
...     return examples

>>> dataset.set_transform(transforms)

>>> image = np.array(dataset[index]["pixel_values"])
>>> mask = np.array(dataset[index]["label"])

>>> visualize_seg_mask(image, mask)

>>> from torchvision.transforms import Resize, ColorJitter, Compose

>>> transformation_chain = Compose([
...     Resize((256, 256)),
...     ColorJitter(brightness=0.25, contrast=0.25, saturation=0.25, hue=0.1)
... ])
>>> resize = Resize((256, 256))

>>> def train_transforms(example_batch):
...     example_batch["pixel_values"] = [transformation_chain(x) for x in example_batch["image"]]
...     example_batch["label"] = [resize(x) for x in example_batch["annotation"]]
...     return example_batch

>>> dataset.set_transform(train_transforms)

>>> image = np.array(dataset[index]["pixel_values"])
>>> mask = np.array(dataset[index]["label"])

>>> visualize_seg_mask(image, mask)