dgs.utils.image.load_image_list

dgs.utils.image.load_image_list(filepath: str | tuple[str, ...], dtype: torch.dtype = torch.float32, device: torch.device = 'cpu', read_mode: torchvision.io.ImageReadMode = torchvision.io.ImageReadMode.RGB) → list[torchvision.tv_tensors.Image | torch.Tensor][source]

Load multiple images with possibly different sizes as a list of tv_tensor images.

Parameters:

  • filepath – Single string or list of absolute or local filepaths to the image.

  • dtype – The dtype of the image, most likely one of uint8, byte, or float32. Default torch.float32.

  • device – Device the image should be on. Default “cpu”

  • read_mode – Which ImageReadMode to use while loading the images. Default ‘ImageReadMode.RGB’.

Returns:

A list of tv_tensor images with the provided dtype on the device. All images are four-dimensional wit a leading batch dimension of 1, like: [1 x C x H x W].