Merge pull request #20535 from SamFC10:onnx-q

dnn : int8 quantized layers support in onnx importer

* added quantized layers support in onnx importer

* added more cases in eltwise node, some more checks

* added tests for quantized nodes

* relax thresholds for failed tests, address review comments

* refactoring based on review comments

* added support for unsupported cases and pre-quantized resnet50 test

* relax thresholds due to int8 resize layer
This commit is contained in:
Jebastin Nadar
2021-10-04 23:37:38 +05:30
committed by GitHub
parent 9085b933d8
commit cce78cc5e2
9 changed files with 795 additions and 54 deletions
@@ -387,6 +387,13 @@ CV__DNN_INLINE_NS_BEGIN
static Ptr<DequantizeLayer> create(const LayerParams &params);
};
class CV_EXPORTS RequantizeLayer : public Layer
{
public:
float scale, shift;
static Ptr<RequantizeLayer> create(const LayerParams &params);
};
class CV_EXPORTS ConcatLayer : public Layer
{
public: