CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : fix idefics3 preprocessing (#16806)

Browse Source 
* mtmd : fix idefics3 preprocessing

* disable granite test

* fix test for granite
This commit is contained in:
Xuan-Son Nguyen
2025-10-27 23:12:16 +01:00
committed by GitHub
parent 5a4ff43e7d
commit e1ab084803
2 changed files with 12 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/mtmd/clip.cpp
View File

@@ -171,7 +171,7 @@ struct clip_hparams {
int32_t n_head;
int32_t n_layer;
// idefics3
int32_t preproc_image_size = 0;
int32_t preproc_image_size = 0; // aka max_dimension
int32_t proj_scale_factor = 0;
float image_mean[3];
@@ -3221,8 +3221,8 @@ struct image_manipulation {
return {0, 0};
}
float scale = std::min(1.0f, std::min(static_cast<float>(max_dimension) / inp_size.width,
static_cast<float>(max_dimension) / inp_size.height));
float scale = std::min(static_cast<float>(max_dimension) / inp_size.width,
static_cast<float>(max_dimension) / inp_size.height);
float target_width_f = static_cast<float>(inp_size.width) * scale;
float target_height_f = static_cast<float>(inp_size.height) * scale;
@@ -3385,7 +3385,7 @@ struct llava_uhd {
// resize to overview size
clip_image_u8_ptr resized_img(clip_image_u8_init());
image_manipulation::bicubic_resize(*img, *resized_img, inst.overview_size.width, inst.overview_size.height);
image_manipulation::resize_and_pad_image(*img, *resized_img, inst.overview_size);
output.push_back(std::move(resized_img));
if (inst.slices.empty()) {
// no slices, just return the resized image
@@ -3587,6 +3587,9 @@ bool clip_image_preprocess(struct clip_ctx * ctx, const clip_image_u8 * img, str
// CITE: https://github.com/huggingface/transformers/blob/main/src/transformers/models/idefics3/image_processing_idefics3.py#L737
const clip_image_size refined_size = image_manipulation::calc_size_preserved_ratio(
original_size, params.image_size, params.preproc_image_size);
// LOG_INF("%s: original size: %d x %d, refined size: %d x %d\n",
// __func__, original_size.width, original_size.height,
// refined_size.width, refined_size.height);
llava_uhd::slice_instructions instructions;
instructions.overview_size = clip_image_size{params.image_size, params.image_size};
@@ -3597,6 +3600,7 @@ bool clip_image_preprocess(struct clip_ctx * ctx, const clip_image_u8 * img, str
};
for (int y = 0; y < refined_size.height; y += params.image_size) {
for (int x = 0; x < refined_size.width; x += params.image_size) {
// LOG_INF("%s: adding slice at x=%d, y=%d\n", __func__, x, y);
instructions.slices.push_back(llava_uhd::slice_coordinates{
/* x */x,
/* y */y,

5
tools/mtmd/tests.sh
View File

@@ -139,7 +139,10 @@ for i in "${!arr_hf[@]}"; do
echo "$output" > $SCRIPT_DIR/output/$bin-$(echo "$hf" | tr '/' '-').log
if echo "$output" | grep -iq "new york"; then
# either contains "new york" or both "men" and "walk"
if echo "$output" | grep -iq "new york" \
|| (echo "$output" | grep -iq "men" && echo "$output" | grep -iq "walk")
then
result="$prefix \033[32mOK\033[0m: $bin $hf"
else
result="$prefix \033[31mFAIL\033[0m: $bin $hf"