def _tensorize()

in src/datasets/formatting/np_formatter.py [0:0]

• 25 lines of code
• 18 McCabe index (conditional complexity)

    def _tensorize(self, value):
        if isinstance(value, (str, bytes, type(None))):
            return value
        elif isinstance(value, (np.character, np.ndarray)) and np.issubdtype(value.dtype, np.character):
            return value
        elif isinstance(value, np.number):
            return value

        default_dtype = {}

        if isinstance(value, np.ndarray) and np.issubdtype(value.dtype, np.integer):
            default_dtype = {"dtype": np.int64}
        elif isinstance(value, np.ndarray) and np.issubdtype(value.dtype, np.floating):
            default_dtype = {"dtype": np.float32}

        if config.PIL_AVAILABLE and "PIL" in sys.modules:
            import PIL.Image

            if isinstance(value, PIL.Image.Image):
                return np.asarray(value, **self.np_array_kwargs)
        if config.TORCHVISION_AVAILABLE and "torchvision" in sys.modules:
            from torchvision.io import VideoReader

            if isinstance(value, VideoReader):
                return value  # TODO(QL): set output to np arrays ?
        if config.TORCHCODEC_AVAILABLE and "torchcodec" in sys.modules:
            from torchcodec.decoders import AudioDecoder, VideoDecoder

            if isinstance(value, (VideoDecoder, AudioDecoder)):
                return value  # TODO(QL): set output to np arrays ?

        return np.asarray(value, **{**default_dtype, **self.np_array_kwargs})