janus/janusflow/models/modeling_vlm.py [171:194]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def prepare_inputs_embeds(
        self,
        input_ids: torch.LongTensor,
        pixel_values: torch.FloatTensor,
        images_seq_mask: torch.LongTensor,
        images_emb_mask: torch.LongTensor,
        **kwargs,
    ):
        """

        Args:
            input_ids (torch.LongTensor): [b, T]
            pixel_values (torch.FloatTensor):   [b, n_images, 3, h, w]
            images_seq_mask (torch.BoolTensor): [b, T]
            images_emb_mask (torch.BoolTensor): [b, n_images, n_image_tokens]

            assert torch.sum(images_seq_mask) == torch.sum(images_emb_mask)

        Returns:
            input_embeds (torch.Tensor): [b, T, D]
        """

        bs, n = pixel_values.shape[0:2]
        images = rearrange(pixel_values, "b n c h w -> (b n) c h w")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



janus/models/modeling_vlm.py [221:244]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def prepare_inputs_embeds(
        self,
        input_ids: torch.LongTensor,
        pixel_values: torch.FloatTensor,
        images_seq_mask: torch.LongTensor,
        images_emb_mask: torch.LongTensor,
        **kwargs,
    ):
        """

        Args:
            input_ids (torch.LongTensor): [b, T]
            pixel_values (torch.FloatTensor):   [b, n_images, 3, h, w]
            images_seq_mask (torch.BoolTensor): [b, T]
            images_emb_mask (torch.BoolTensor): [b, n_images, n_image_tokens]

            assert torch.sum(images_seq_mask) == torch.sum(images_emb_mask)

        Returns:
            input_embeds (torch.Tensor): [b, T, D]
        """

        bs, n = pixel_values.shape[0:2]
        images = rearrange(pixel_values, "b n c h w -> (b n) c h w")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -