mtmd : match the transformers Qwen-VL resize (#30736)

This commit is contained in:
bosh authored and GitHub committed 2026-10-20 01:14:40 +02:00
1 parent 921257f500
commit f711c8f303
5 files changed
+52 -9

No files matched your search

+25
View File
@@ -66,6 +66,31 @@ MAKE_TEST(test_image_preprocessor_longest_edge) {
}
}
MAKE_TEST(test_image_preprocessor_dyn_size) {
// { patch_size, image size, expected size }
// a side that is an even number plus .5 merged patches rounds down, like Python round() in smart_resize
const std::vector<std::tuple<int, clip_image_size, clip_image_size>> cases = {
{ 16, { 768, 400 }, { 768, 384 } },
{ 16, { 800, 336 }, { 800, 320 } },
{ 16, { 400, 400 }, { 384, 384 } },
{ 16, { 640, 240 }, { 640, 256 } },
{ 14, { 966, 560 }, { 952, 560 } },
};
for (const auto & [patch_size, input, expected] : cases) {
clip_hparams hparams;
hparams.patch_size = patch_size;
hparams.n_merge = 2;
hparams.image_round_half_even = true;
hparams.set_limit_image_tokens(8, 4096);
const clip_image_size actual = mtmd_image_preprocessor_dyn_size::get_target_size(hparams, input);
const std::string name = std::to_string(input.width) + "x" + std::to_string(input.height);
t.assert_equal(name + " width", expected.width, actual.width);
t.assert_equal(name + " height", expected.height, actual.height);
}
}
MAKE_TEST(test_image_preprocessor_lfm2) {
clip_hparams hparams;
hparams.patch_size = 16;