potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 07:13:02 +04:00
Code Packages Releases Wiki Activity

Merge pull request #28741 from abhishek-gola:int8_block_layout

Browse Source 
Int8 block layout support #28741

After this patch we got the following speed ups on **resnet50-qdq.onnx** model.

- Inference time now: **_~6.6ms_** (inference time using onnxruntime is ~5.7ms).
- Inference time before: _**~11.5ms**_ [after QDQ PR #28595]
- Speed up: _**~42.6% or 1.74x**_
- Device details:
- Model name: Intel(R) Core(TM) i9-14900KS, x86, 32 Cores, ubuntu 24.04, 

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Abhishek Gola
2026-04-12 22:10:03 +05:30
committed by GitHub
parent 1a6f669763
commit 53d9a67cf3
11 changed files with 3092 additions and 406 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/test/test_model.cpp
+57
View File
@@ -921,4 +921,61 @@ TEST_P(Reproducibility_ResNet50_ONNX, Accuracy)
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_ResNet50_ONNX,
testing::ValuesIn(getAvailableTargets(DNN_BACKEND_OPENCV)));
typedef testing::TestWithParam<Target> Reproducibility_ResNet50_QDQ_ONNX;
TEST_P(Reproducibility_ResNet50_QDQ_ONNX, Accuracy)
{
Target targetId = GetParam();
applyTestTag(targetId == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_512MB : CV_TEST_TAG_MEMORY_1GB);
ASSERT_TRUE(ocl::useOpenCL() || targetId == DNN_TARGET_CPU || targetId == DNN_TARGET_CPU_FP16);
std::string modelname = _tf("onnx/models/resnet50-v1-12-qdq.onnx", false);
Net net = readNetFromONNX(modelname);
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setPreferableTarget(targetId);
if (targetId == DNN_TARGET_CPU_FP16)
net.enableWinograd(false);
std::string imgname = _tf("sqcat.png");
Mat image = imread(imgname);
Mat input = blobFromImage(image, 0.017, Size(224,224),
Scalar(103.939, 116.779, 123.68),
false, true, CV_32F);
ASSERT_TRUE(!input.empty());
Mat out;
double min_t = 0;
const int niters =
#ifdef _DEBUG
1;
#else
30;
#endif
for (int i = 0; i < niters; i++) {
double t = (double)getTickCount();
net.setInput(input);
out = net.forward();
t = (double)getTickCount() - t;
min_t = i == 0 ? t : std::min(min_t, t);
}
printf("run time = %.2fms\n", min_t*1000./getTickFrequency());
const int K = 5;
std::vector<std::pair<int, float> > res;
topK(out, res, K);
ASSERT_EQ(int(res.size()), K);
std::vector<std::pair<int, float> > ref = {{285, 10.44}, {287, 10.13}, {283, 8.89}, {278, 8.43}};
const float eps = 0.5f;
for (int i = 0; i < (int)ref.size(); i++) {
EXPECT_EQ(ref[i].first, res[i].first);
EXPECT_NEAR(ref[i].second, res[i].second, eps);
}
}
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_ResNet50_QDQ_ONNX,
testing::ValuesIn(getAvailableTargets(DNN_BACKEND_OPENCV)));
}} // namespace