potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00
Code Packages Releases Wiki Activity

Merge pull request #18891 from CowKeyMan:NMS_boxes_with_different_labels

Browse Source 
Add option for NMS for boxes with different labels

* DetectionModel impl

* Add option for NMS for boxes with different labels

In the detect function in modules/dnn/include/opencv2/dnn/dnn.hpp, whose implementation can be found at modules/dnn/src/model.cpp, the Non Max Suppression (NMS) is applied only for objects of the same label. Thus, a flag
was added with the purpose to allow developers to choose if they want to keep the default implementation or wether they would like NMS to be applied to all the boxes, regardless of label.

The flag is called nmsDifferentLabels, and is given a default value of false, which applies the current default implementation, thus allowing existing projects to update opencv without disruption

Solves issue opencv#18832

* Change return type of set & Add default constr

* Add assertions due to default constructor
This commit is contained in:
Daniel Cauchi
2020-12-01 14:50:24 +01:00
committed by GitHub
parent 3f686a6ab8
commit 9d37cdaa66
3 changed files with 165 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/test/test_model.cpp
+56 -1
View File
@@ -25,7 +25,8 @@ public:
double scoreDiff, double iouDiff,
double confThreshold = 0.24, double nmsThreshold = 0.0,
const Size& size = {-1, -1}, Scalar mean = Scalar(),
double scale = 1.0, bool swapRB = false, bool crop = false)
double scale = 1.0, bool swapRB = false, bool crop = false,
bool nmsAcrossClasses = false)
{
checkBackend();
@@ -38,6 +39,8 @@ public:
model.setPreferableBackend(backend);
model.setPreferableTarget(target);
model.setNmsAcrossClasses(nmsAcrossClasses);
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
@@ -177,6 +180,58 @@ TEST_P(Test_Model, DetectRegion)
Scalar(), scale, swapRB);
}
TEST_P(Test_Model, DetectRegionWithNmsAcrossClasses)
{
applyTestTag(CV_TEST_TAG_LONG, CV_TEST_TAG_MEMORY_1GB);
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2020040000) // nGraph compilation failure
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_GE(2019010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16);
#endif
#if defined(INF_ENGINE_RELEASE)
if (target == DNN_TARGET_MYRIAD
&& getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X);
#endif
std::vector<int> refClassIds = { 6, 11 };
std::vector<float> refConfidences = { 0.750469f, 0.901615f };
std::vector<Rect2d> refBoxes = { Rect2d(240, 53, 135, 72),
Rect2d(58, 141, 117, 249) };
std::string img_path = _tf("dog416.png");
std::string weights_file = _tf("yolo-voc.weights", false);
std::string config_file = _tf("yolo-voc.cfg");
double scale = 1.0 / 255.0;
Size size{ 416, 416 };
bool swapRB = true;
bool crop = false;
bool nmsAcrossClasses = true;
double confThreshold = 0.24;
double nmsThreshold = (target == DNN_TARGET_MYRIAD) ? 0.15: 0.15;
double scoreDiff = 8e-5, iouDiff = 1e-5;
if (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD || target == DNN_TARGET_CUDA_FP16)
{
scoreDiff = 1e-2;
iouDiff = 1.6e-2;
}
testDetectModel(weights_file, config_file, img_path, refClassIds, refConfidences,
refBoxes, scoreDiff, iouDiff, confThreshold, nmsThreshold, size,
Scalar(), scale, swapRB, crop,
nmsAcrossClasses);
}
TEST_P(Test_Model, DetectionOutput)
{
#if defined(INF_ENGINE_RELEASE)