Method slice_image

tools/mtmd/mtmd-image.cpp:688–729

}

std::vector<clip_image_u8_ptr> mtmd_image_preprocessor_llava_uhd::slice_image(const clip_image_u8 & img, const mtmd_image_preprocessor_llava_uhd::slice_instructions & inst, bool overview_first) {
    std::vector<clip_image_u8_ptr> output;

    // resize to overview size
    clip_image_u8_ptr resized_img(clip_image_u8_init());
    img_tool::resize(img, *resized_img, inst.overview_size, hparams.image_resize_algo_ov,
                        hparams.image_pad_ov, hparams.image_pad_color_ov);
    if (overview_first) {
        output.push_back(std::move(resized_img));
    }

    if (inst.slices.empty()) {
        // no slices, just return the resized image
        if (!overview_first) {
            output.push_back(std::move(resized_img));
        }
        return output;
    }

    // resize to refined size
    clip_image_u8_ptr refined_img(clip_image_u8_init());
    img_tool::resize(img, *refined_img, inst.refined_size, hparams.image_resize_algo_rf,
                        hparams.image_pad_rf, hparams.image_pad_color_rf);

    // create slices
    for (const auto & slice : inst.slices) {
        int x = slice.x;
        int y = slice.y;
        int w = slice.size.width;
        int h = slice.size.height;

        clip_image_u8_ptr img_slice(clip_image_u8_init());
        img_tool::crop(*refined_img, *img_slice, x, y, w, h);
        output.push_back(std::move(img_slice));
    }

    if (!overview_first) {
        output.push_back(std::move(resized_img));
    }

    return output;
}

clip_image_size mtmd_image_preprocessor_llava_uhd::get_best_resize(const clip_image_size & original_size, int scale_resolution, int patch_size, bool allow_upscale) {
    int width  = original_size.width;