SafeTensorsReader

class vision_architectures.image_readers.safetensors_reader.SafetensorsReader(image_key='images', spacing_key='spacing', other_keys=None, add_channel_dim=True, dtype=torch.float32)

Bases: ImageReader

__init__(image_key='images', spacing_key='spacing', other_keys=None, add_channel_dim=True, dtype=torch.float32)

verify_suffix(filename)

Verify whether the specified filename is supported by the current reader. This method should return True if the reader is able to read the format suggested by the filename.

Parameters:

filename – file name or a list of file names to read. if a list of files, verify all the suffixes.

read(filepath)

Read image data from specified file or files. Note that it returns a data object or a sequence of data objects.

Parameters:

• data – file name or a list of file names to read.

• kwargs – additional args for actual read API of 3rd party libs.

Return type:

dict[str, Union[Tensor, Any]]

get_data(datapoint)

Extract data array and metadata from loaded image and return them. This function must return two objects, the first is a numpy array of image data, the second is a dictionary of metadata.

Parameters:

img – an image object loaded from an image file or a list of image objects.