Add ResizeLayerRT plugin

Signed-off-by: nvidia <micaelaverucchi@gmail.com>

include/tkDNN/NetworkRT.h

@@ -30,6 +30,7 @@ using namespace nvinfer1;
 #include "pluginsRT/ShortcutRT.h"
 #include "pluginsRT/YoloRT.h"
 #include "pluginsRT/UpsampleRT.h"
+#include "pluginsRT/ResizeLayerRT.h"
 //#include "pluginsRT/Int8Calibrator.h"
 
 class PluginFactory : IPluginFactory

include/tkDNN/Yolo3Detection.h

@@ -33,6 +33,7 @@ class Yolo3Detection {
     public:
         int classes = 0;
         int num = 0;
+        int n_masks = 0;
         float thresh = 0.3;
         cv::Scalar colors[256];
 

include/tkDNN/kernels.h

@@ -9,6 +9,9 @@ void activationLOGISTICForward(dnnType* srcData, dnnType* dstData, int size, cud
 
 void fill(dnnType* data, int size, dnnType val, cudaStream_t stream = cudaStream_t(0));
 
+void resizeForward(  dnnType* srcData, dnnType* dstData, int n, int i_c, int i_h, int i_w,
+                    int o_c, int o_h, int o_w, cudaStream_t stream = cudaStream_t(0));
+
 void reorgForward(  dnnType* srcData, dnnType* dstData, 
                     int n, int c, int h, int w, int stride, cudaStream_t stream = cudaStream_t(0));
 void softmaxForward(float *input, int n, int batch, int batch_offset, 

include/tkDNN/pluginsRT/ResizeLayerRT.h

@@ -0,0 +1,67 @@
+#include<cassert>
+#include "../kernels.h"
+
+class ResizeLayerRT : public IPlugin {
+
+public:
+	ResizeLayerRT(int c, int h, int w) {
+		o_c = c;
+		o_h = h;
+		o_w = w;	
+	}
+
+	~ResizeLayerRT(){
+	}
+
+	int getNbOutputs() const override {
+		return 1;
+	}
+
+	Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) override {
+		return DimsCHW{o_c, o_h, o_w};
+	}
+
+	void configure(const Dims* inputDims, int nbInputs, const Dims* outputDims, int nbOutputs, int maxBatchSize) override {
+		i_c = inputDims[0].d[0];
+		i_h = inputDims[0].d[1];
+		i_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 {
+    	// printf("%d %d %d %d %d %d\n", i_c, i_w, i_h, o_c, o_w, o_h);
+        resizeForward((dnnType*)reinterpret_cast<const dnnType*>(inputs[0]), 
+					  reinterpret_cast<dnnType*>(outputs[0]), 
+					  batchSize, i_c, i_h, i_w, o_c, o_h, o_w, stream);
+		return 0;
+	}
+
+
+	virtual size_t getSerializationSize() override {
+		return 6*sizeof(int);
+	}
+
+	virtual void serialize(void* buffer) override {
+		char *buf = reinterpret_cast<char*>(buffer);
+
+		tk::dnn::writeBUF(buf, o_c);
+		tk::dnn::writeBUF(buf, o_h);
+		tk::dnn::writeBUF(buf, o_w);
+
+		tk::dnn::writeBUF(buf, i_c);
+		tk::dnn::writeBUF(buf, i_h);
+		tk::dnn::writeBUF(buf, i_w);
+	}
+
+	int i_c, i_h, i_w, o_c, o_h, o_w;
+};