def get_vision_position_ids()

in optimum/exporters/openvino/model_configs.py [0:0]

• 27 lines of code
• 2 McCabe index (conditional complexity)

    def get_vision_position_ids(self):
        # Adopted from https://github.com/huggingface/transformers/blob/v4.51.3/src/transformers/models/phi4_multimodal/modeling_phi4_multimodal.py#L494-L512
        import torch

        batch_size = self.batch_size
        max_im_h, max_im_w = self.height, self.width
        max_nb_patches_h, max_nb_patches_w = max_im_h // self.patch_size, max_im_w // self.patch_size
        boundaries = torch.arange(1 / self.num_patches_per_side, 1.0, 1 / self.num_patches_per_side)
        position_ids = torch.full(
            size=(
                batch_size,
                max_nb_patches_h * max_nb_patches_w,
            ),
            fill_value=0,
        )
        patch_attention_mask = torch.ones(
            [self.batch_size, self.height // self.patch_size, self.width // self.patch_size], dtype=torch.int64
        )
        patch_attention_mask[0, self.height - 2 :] = 0

        for batch_idx, p_attn_mask in enumerate(patch_attention_mask):
            nb_patches_h = p_attn_mask[:, 0].sum()
            nb_patches_w = p_attn_mask[0].sum()

            fractional_coords_h = torch.arange(0, 1 - 1e-6, 1 / nb_patches_h)
            fractional_coords_w = torch.arange(0, 1 - 1e-6, 1 / nb_patches_w)

            bucket_coords_h = torch.bucketize(fractional_coords_h, boundaries, right=True)
            bucket_coords_w = torch.bucketize(fractional_coords_w, boundaries, right=True)

            pos_ids = (bucket_coords_h[:, None] * self.num_patches_per_side + bucket_coords_w).flatten()
            position_ids[batch_idx][p_attn_mask.view(-1)] = pos_ids
        return position_ids