shortcut rt test

src/NetworkRT.cpp

@@ -14,6 +14,7 @@ using namespace nvinfer1;
 #include "pluginsRT/ActivationLeakyRT.cpp"
 #include "pluginsRT/ReorgRT.cpp"
 #include "pluginsRT/RegionRT.cpp"
+#include "pluginsRT/ShortcutRT.cpp"
 #include "pluginsRT/Int8Calibrator.cpp"
 
 // Logger for info/warning/errors
@@ -167,6 +168,8 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Layer *l) {
         return convert_layer(input, (Reorg*) l);
     if(type == LAYER_REGION)
         return convert_layer(input, (Region*) l);
+    if(type == LAYER_SHORTCUT)
+        return convert_layer(input, (Shortcut*) l);
 
     FatalError("Layer not implemented in tensorRT");
     return NULL;
@@ -321,6 +324,18 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Region *l) {
     return lRT;
 }
 
+ILayer* NetworkRT::convert_layer(ITensor *input, Shortcut *l) {
+    //std::cout<<"convert Shortcut\n";
+
+    //std::cout<<"New plugin Shortcut\n";
+    ITensor *tens = tensors[l->backLayer];
+    IPlugin *plugin = new ShortcutRT(tens);
+    IPluginLayer *lRT = networkRT->addPlugin(&input, 1, *plugin);
+    checkNULL(lRT);
+    return lRT;
+}
+
+
 bool NetworkRT::serialize(const char *filename) {
 
     std::ofstream p(filename);

src/pluginsRT/ShortcutRT.cpp

@@ -0,0 +1,64 @@
+#include<cassert>
+#include "kernels.h"
+
+class ShortcutRT : public IPlugin {
+
+public:
+	ShortcutRT(ITensor *tens) {
+		this->back_layer = tens;
+	}
+
+	~ShortcutRT(){
+
+	}
+
+	int getNbOutputs() const override {
+		return 1;
+	}
+
+	Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) override {
+		return DimsCHW{inputs[0].d[0], inputs[0].d[1], inputs[0].d[2]};
+	}
+
+	void configure(const Dims* inputDims, int nbInputs, const Dims* outputDims, int nbOutputs, int maxBatchSize) override {
+		c = inputDims[0].d[0];
+		h = inputDims[0].d[1];
+		w = inputDims[0].d[2];
+	}
+
+	int initialize() override {
+
+		return 0;
+	}
+
+	virtual void terminate() override {
+	}
+
+	virtual size_t getWorkspaceSize(int maxBatchSize) const override {
+		return 0;
+	}
+
+	virtual int enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream) override {
+
+		dnnType *srcData = (dnnType*)reinterpret_cast<const dnnType*>(inputs[0]);
+		dnnType *dstData = reinterpret_cast<dnnType*>(outputs[0]);
+
+		checkCuda( cudaMemcpyAsync(dstData, srcData, batchSize*c*h*w*sizeof(dnnType), cudaMemcpyDeviceToDevice, stream));
+		return 0;
+	}
+
+
+	virtual size_t getSerializationSize() override {
+		return 3*sizeof(int);
+	}
+
+	virtual void serialize(void* buffer) override {
+		char *buf = reinterpret_cast<char*>(buffer);
+		tk::dnn::writeBUF(buf, c);
+		tk::dnn::writeBUF(buf, h);
+		tk::dnn::writeBUF(buf, w);
+	}
+
+	int c, h, w;
+	ITensor *back_layer;
+};