Shelfnet works on cuDNN. To test everything else

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

include/tkDNN/Layer.h

@@ -21,6 +21,7 @@ enum layerType_t {
     LAYER_ACTIVATION_MISH,
     LAYER_FLATTEN,
     LAYER_RESHAPE,
+    LAYER_RESIZE,
     LAYER_MULADD,
     LAYER_POOLING,
     LAYER_SOFTMAX,
@@ -70,6 +71,7 @@ public:
             case LAYER_ACTIVATION_MISH:     return "ActivationMish";
             case LAYER_FLATTEN:             return "Flatten";
             case LAYER_RESHAPE:             return "Reshape";
+            case LAYER_RESIZE:              return "Resize";
             case LAYER_MULADD:              return "MulAdd";
             case LAYER_POOLING:             return "Pooling";
             case LAYER_SOFTMAX:             return "Softmax";
@@ -427,6 +429,19 @@ public:
 
 };
 
+/**
+    Resize layer
+*/
+class Resize : public Layer {
+
+public:
+    Resize(Network *net, int scale_c, int scale_h, int scale_w, bool fixed=false);
+    virtual ~Resize();
+    virtual layerType_t getLayerType() { return LAYER_RESIZE; };
+
+    virtual dnnType* infer(dataDim_t &dim, dnnType* srcData);
+
+};
 
 /**
     MulAdd layer
@@ -545,7 +560,7 @@ public:
 class Shortcut : public Layer {
 
 public:
-    Shortcut(Network *net, Layer *backLayer); 
+    Shortcut(Network *net, Layer *backLayer, bool mul=false); 
     virtual ~Shortcut();
     virtual layerType_t getLayerType() { return LAYER_SHORTCUT; };
 
@@ -553,6 +568,7 @@ public:
 
 public:
     Layer *backLayer;
+    bool mul = false;
 };
 
 /**

include/tkDNN/kernels.h

@@ -24,7 +24,7 @@ void softmaxForward(float *input, int n, int batch, int batch_offset,
                     int groups, int group_offset, int stride, float temp, float *output, cudaStream_t stream = cudaStream_t(0));
 
 void shortcutForward(dnnType *srcData, dnnType *dstData, int n1, int c1, int h1, int w1, int s1,
-                     int n2, int c2, int h2, int w2, int s2,
+                     int n2, int c2, int h2, int w2, int s2, bool mul,
                      cudaStream_t stream = cudaStream_t(0));
 
 void upsampleForward(dnnType *srcData, dnnType *dstData,

include/tkDNN/pluginsRT/ShortcutRT.h

@@ -4,10 +4,11 @@
 class ShortcutRT : public IPlugin {
 
 public:
-	ShortcutRT(tk::dnn::dataDim_t bdim) {
+	ShortcutRT(tk::dnn::dataDim_t bdim, bool mul) {
 		this->bc = bdim.c;
 		this->bh = bdim.h;
 		this->bw = bdim.w;
+		this->mul = mul;
 	}
 
 	~ShortcutRT(){
@@ -47,15 +48,14 @@ public:
 		dnnType *dstData = reinterpret_cast<dnnType*>(outputs[0]);
 
 		checkCuda( cudaMemcpyAsync(dstData, srcData, batchSize*c*h*w*sizeof(dnnType), cudaMemcpyDeviceToDevice, stream));
-		for(int b=0; b < batchSize; ++b)
-			shortcutForward(srcDataBack + b*bc*bh*bw, dstData + b*c*h*w, 1, c, h, w, 1, 1, bc, bh, bw, 1, stream);
+		shortcutForward(srcDataBack, dstData, batchSize, c, h, w, 1, batchSize, bc, bh, bw, 1, mul, stream);
 
 		return 0;
 	}
 
 
 	virtual size_t getSerializationSize() override {
-		return 6*sizeof(int);
+		return 6*sizeof(int) + sizeof(bool);
 	}
 
 	virtual void serialize(void* buffer) override {
@@ -63,12 +63,14 @@ public:
 		tk::dnn::writeBUF(buf, bc);
 		tk::dnn::writeBUF(buf, bh);
 		tk::dnn::writeBUF(buf, bw);
+		tk::dnn::writeBUF(buf, mul);
 		tk::dnn::writeBUF(buf, c);
 		tk::dnn::writeBUF(buf, h);
 		tk::dnn::writeBUF(buf, w);
-		
+			
 	}
 
 	int c, h, w;
 	int bc, bh, bw;
+	bool mul;
 };