read_image

torchvision.io.read_image(path: str, mode: ImageReadMode = ImageReadMode.UNCHANGED, apply_exif_orientation: bool = False) → Tensor

Reads a JPEG, PNG or GIF image into a 3 dimensional RGB or grayscale Tensor.

The values of the output tensor are in uint8 in [0, 255] for most cases. If the image is a 16-bit png, then the output tensor is uint16 in [0, 65535] (supported from torchvision 0.21. Since uint16 support is limited in pytorch, we recommend calling torchvision.transforms.v2.functional.to_dtype() with scale=True after this function to convert the decoded image into a uint8 or float tensor.

Parameters:

• path (str or pathlib.Path) – path of the JPEG, PNG or GIF image.

• mode (ImageReadMode) – the read mode used for optionally converting the image. Default: ImageReadMode.UNCHANGED. See ImageReadMode class for more information on various available modes. Ignored for GIFs.

• apply_exif_orientation (bool) – apply EXIF orientation transformation to the output tensor. Ignored for GIFs. Default: False.

Returns:

output (Tensor[image_channels, image_height, image_width])

Examples using read_image:

Getting started with transforms v2

Getting started with transforms v2

Repurposing masks into bounding boxes

Repurposing masks into bounding boxes

Torchscript support

Torchscript support

Visualization utilities

Visualization utilities