decode_gif

torchvision.io.decode_gif(input: Tensor) → Tensor

Decode a GIF image into a 3 or 4 dimensional RGB Tensor.

The values of the output tensor are uint8 between 0 and 255. The output tensor has shape (C, H, W) if there is only one image in the GIF, and (N, C, H, W) if there are N images.

Parameters:

input (Tensor[1]) – a one dimensional contiguous uint8 tensor containing the raw bytes of the GIF image.

Returns:

output (Tensor[image_channels, image_height, image_width] or Tensor[num_images, image_channels, image_height, image_width])