def __call__()

in src/transformers/data/datasets/transforms/volume_transforms.py [0:0]

• 32 lines of code
• 10 McCabe index (conditional complexity)

    def __call__(self, clip):
        """
        Args: clip (list of numpy.ndarray): clip (list of images)
        to be converted to tensor.
        """
        # Retrieve shape
        if isinstance(clip[0], np.ndarray):
            h, w, ch = clip[0].shape
            assert ch == self.channel_nb, 'Got {0} instead of 3 channels'.format(
                ch)
        elif isinstance(clip[0], Image.Image):
            w, h = clip[0].size
        else:
            raise TypeError('Expected numpy.ndarray or PIL.Image\
            but got list of {0}'.format(type(clip[0])))

        np_clip = np.zeros([self.channel_nb, len(clip), int(h), int(w)])

        # Convert
        for img_idx, img in enumerate(clip):
            if isinstance(img, np.ndarray):
                pass
            elif isinstance(img, Image.Image):
                img = np.array(img, copy=False)
            else:
                raise TypeError('Expected numpy.ndarray or PIL.Image\
                but got list of {0}'.format(type(clip[0])))
            img = convert_img(img)
            np_clip[:, img_idx, :, :] = img
        if self.numpy:
            if self.div_255:
                np_clip = np_clip / 255.0
            return np_clip

        else:
            tensor_clip = torch.from_numpy(np_clip)

            if not isinstance(tensor_clip, torch.FloatTensor):
                tensor_clip = tensor_clip.float()
            if self.div_255:
                tensor_clip = torch.div(tensor_clip, 255)
            return tensor_clip