pip install -U albumentations 

>>> from datasets import load_dataset

>>> train_dataset = load_dataset("sayakpaul/nyu_depth_v2", split="train")
>>> index = 17
>>> example = train_dataset[index]
>>> example
{'image': <PIL.PngImagePlugin.PngImageFile image mode=RGB size=640x480>,
 'depth_map': <PIL.TiffImagePlugin.TiffImageFile image mode=F size=640x480>}

>>> from datasets import Image

>>> train_dataset = train_dataset.cast_column("depth_map", Image(mode="F"))

>>> example["image"]

>>> example["depth_map"].convert("RGB")

>>> import numpy as np
>>> import matplotlib.pyplot as plt

>>> cmap = plt.cm.viridis

>>> def colored_depthmap(depth, d_min=None, d_max=None):
...     if d_min is None:
...         d_min = np.min(depth)
...     if d_max is None:
...         d_max = np.max(depth)
...     depth_relative = (depth - d_min) / (d_max - d_min)
...     return 255 * cmap(depth_relative)[:,:,:3]

>>> def show_depthmap(depth_map):
...    if not isinstance(depth_map, np.ndarray):
...        depth_map = np.array(depth_map)
...    if depth_map.ndim == 3:
...        depth_map = depth_map.squeeze()

...    d_min = np.min(depth_map)
...    d_max = np.max(depth_map)
...    depth_map = colored_depthmap(depth_map, d_min, d_max)

...    plt.imshow(depth_map.astype("uint8"))
...    plt.axis("off")
...    plt.show()

>>> show_depthmap(example["depth_map"])

>>> def merge_into_row(input_image, depth_target):
...     if not isinstance(input_image, np.ndarray):
...         input_image = np.array(input_image)
...
...     d_min = np.min(depth_target)
...     d_max = np.max(depth_target)
...     depth_target_col = colored_depthmap(depth_target, d_min, d_max)
...     img_merge = np.hstack([input_image, depth_target_col])
...
...     return img_merge

>>> random_indices = np.random.choice(len(train_dataset), 9).tolist()
>>> plt.figure(figsize=(15, 6))
>>> for i, idx in enumerate(random_indices):
...     example = train_dataset[idx]
...     ax = plt.subplot(3, 3, i + 1)
...     image_viz = merge_into_row(
...         example["image"], example["depth_map"]
...     )
...     plt.imshow(image_viz.astype("uint8"))
...     plt.axis("off")

>>> import albumentations as A

>>> crop_size = (448, 576)
>>> transforms = [
...     A.HorizontalFlip(p=0.5),
...     A.RandomCrop(crop_size[0], crop_size[1]),
...     A.RandomBrightnessContrast(),
...     A.RandomGamma(),
...     A.HueSaturationValue()
... ]

>>> additional_targets = {"depth": "mask"}
>>> aug = A.Compose(transforms=transforms, additional_targets=additional_targets)

>>> def apply_transforms(examples):
...     transformed_images, transformed_maps = [], []
...     for image, depth_map in zip(examples["image"], examples["depth_map"]):
...         image, depth_map = np.array(image), np.array(depth_map)
...         transformed = aug(image=image, depth=depth_map)
...         transformed_images.append(transformed["image"])
...         transformed_maps.append(transformed["depth"])
...
...     examples["pixel_values"] = transformed_images
...     examples["labels"] = transformed_maps
...     return examples

>>> train_dataset.set_transform(apply_transforms)

>>> example = train_dataset[index]

>>> plt.imshow(example["pixel_values"])
>>> plt.axis("off")
>>> plt.show()

>>> show_depthmap(example["labels"])

>>> plt.figure(figsize=(15, 6))

>>> for i, idx in enumerate(random_indices):
...     ax = plt.subplot(3, 3, i + 1)
...     example = train_dataset[idx]
...     image_viz = merge_into_row(
...         example["pixel_values"], example["labels"]
...     )
...     plt.imshow(image_viz.astype("uint8"))
...     plt.axis("off")