How to use the batchgenerators.augmentations.utils.interpolate_img function in batchgenerators

if patch_center_dist_from_border[d] == data.shape[d + 2] - patch_center_dist_from_border[d]:
                                ctr = int(patch_center_dist_from_border[d])
                            elif patch_center_dist_from_border[d] < data.shape[d + 2] - patch_center_dist_from_border[d]:
                                ctr = int(np.random.randint(patch_center_dist_from_border[d], data.shape[d + 2] - patch_center_dist_from_border[d]))
                            else:
                                logger.error('low should be <= upper. patch_type:{}, patch_center_dist_from_border:{}, data.shape:{}, ctr_list:{}'.format(str(patch_type), str(patch_center_dist_from_border), str(data.shape), str(ctr_list)))
                    else: # center crop
                        ctr = int(np.round(data.shape[d + 2] / 2.))
                    ctr_list.append(ctr)

                # extracting patch
                if n < 10 and modified_coords:
                    for d in range(dim):
                        coords[d] += ctr_list[d]
                    for channel_id in range(data.shape[1]):
                        data_result[sample_id, channel_id] = interpolate_img(data[sample_id, channel_id], coords, order_data, border_mode_data, cval=border_cval_data)
                    if seg is not None:
                        for channel_id in range(seg.shape[1]):
                            seg_result[sample_id, channel_id] = interpolate_img(seg[sample_id, channel_id], coords, order_seg, border_mode_seg, cval=border_cval_seg, is_seg=True)
                else:
                    augs = list()
                    if seg is None:
                        s = None
                    else:
                        s = seg[sample_id:sample_id + 1]
                    if random_crop:
                        # margin = [patch_center_dist_from_border[d] - patch_size[d] // 2 for d in range(dim)]
                        # d, s = random_crop_aug(data[sample_id:sample_id + 1], s, patch_size, margin)
                        d_tmps = list()
                        for channel_id in range(data.shape[1]):
                            d_tmp = utils.extract_roi_from_volume(data[sample_id, channel_id], ctr_list, patch_size, fill="zero")
                            d_tmps.append(d_tmp)

# now find a nice center location
        if modified_coords:
            for d in range(dim):
                if random_crop:
                    ctr = np.random.uniform(patch_center_dist_from_border[d],
                                            data.shape[d + 2] - patch_center_dist_from_border[d])
                else:
                    ctr = int(np.round(data.shape[d + 2] / 2.))
                coords[d] += ctr
            for channel_id in range(data.shape[1]):
                data_result[sample_id, channel_id] = interpolate_img(data[sample_id, channel_id], coords, order_data,
                                                                     border_mode_data, cval=border_cval_data)
            if seg is not None:
                for channel_id in range(seg.shape[1]):
                    seg_result[sample_id, channel_id] = interpolate_img(seg[sample_id, channel_id], coords, order_seg,
                                                                        border_mode_seg, cval=border_cval_seg,
                                                                        is_seg=True)
        else:
            if seg is None:
                s = None
            else:
                s = seg[sample_id:sample_id + 1]
            if random_crop:
                margin = [patch_center_dist_from_border[d] - patch_size[d] // 2 for d in range(dim)]
                d, s = random_crop_aug(data[sample_id:sample_id + 1], s, patch_size, margin)
            else:
                d, s = center_crop_aug(data[sample_id:sample_id + 1], patch_size, s)
            data_result[sample_id] = d[0]
            if seg is not None:
                seg_result[sample_id] = s[0]

ctr = int(np.random.randint(patch_center_dist_from_border[d], data.shape[d + 2] - patch_center_dist_from_border[d]))
                            else:
                                logger.error('low should be <= upper. patch_type:{}, patch_center_dist_from_border:{}, data.shape:{}, ctr_list:{}'.format(str(patch_type), str(patch_center_dist_from_border), str(data.shape), str(ctr_list)))
                    else: # center crop
                        ctr = int(np.round(data.shape[d + 2] / 2.))
                    ctr_list.append(ctr)

                # extracting patch
                if n < 10 and modified_coords:
                    for d in range(dim):
                        coords[d] += ctr_list[d]
                    for channel_id in range(data.shape[1]):
                        data_result[sample_id, channel_id] = interpolate_img(data[sample_id, channel_id], coords, order_data, border_mode_data, cval=border_cval_data)
                    if seg is not None:
                        for channel_id in range(seg.shape[1]):
                            seg_result[sample_id, channel_id] = interpolate_img(seg[sample_id, channel_id], coords, order_seg, border_mode_seg, cval=border_cval_seg, is_seg=True)
                else:
                    augs = list()
                    if seg is None:
                        s = None
                    else:
                        s = seg[sample_id:sample_id + 1]
                    if random_crop:
                        # margin = [patch_center_dist_from_border[d] - patch_size[d] // 2 for d in range(dim)]
                        # d, s = random_crop_aug(data[sample_id:sample_id + 1], s, patch_size, margin)
                        d_tmps = list()
                        for channel_id in range(data.shape[1]):
                            d_tmp = utils.extract_roi_from_volume(data[sample_id, channel_id], ctr_list, patch_size, fill="zero")
                            d_tmps.append(d_tmp)
                        d = np.asarray(d_tmps)
                        if seg is not None:
                            s_tmps = list()

else:
                sc = np.random.uniform(max(scale[0], 1), scale[1])
            coords = scale_coords(coords, sc)
            modified_coords = True

        # now find a nice center location
        if modified_coords:
            for d in range(dim):
                if random_crop:
                    ctr = np.random.uniform(patch_center_dist_from_border[d],
                                            data.shape[d + 2] - patch_center_dist_from_border[d])
                else:
                    ctr = int(np.round(data.shape[d + 2] / 2.))
                coords[d] += ctr
            for channel_id in range(data.shape[1]):
                data_result[sample_id, channel_id] = interpolate_img(data[sample_id, channel_id], coords, order_data,
                                                                     border_mode_data, cval=border_cval_data)
            if seg is not None:
                for channel_id in range(seg.shape[1]):
                    seg_result[sample_id, channel_id] = interpolate_img(seg[sample_id, channel_id], coords, order_seg,
                                                                        border_mode_seg, cval=border_cval_seg,
                                                                        is_seg=True)
        else:
            if seg is None:
                s = None
            else:
                s = seg[sample_id:sample_id + 1]
            if random_crop:
                margin = [patch_center_dist_from_border[d] - patch_size[d] // 2 for d in range(dim)]
                d, s = random_crop_aug(data[sample_id:sample_id + 1], s, patch_size, margin)
            else:
                d, s = center_crop_aug(data[sample_id:sample_id + 1], patch_size, s)