Add support to Scaled-YOLO4, update Yolov4x-mish (tested)

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

include/tkDNN/Layer.h

@@ -19,6 +19,7 @@ enum layerType_t {
     LAYER_ACTIVATION_CRELU,
     LAYER_ACTIVATION_LEAKY,
     LAYER_ACTIVATION_MISH,
+    LAYER_ACTIVATION_LOGISTIC,
     LAYER_FLATTEN,
     LAYER_RESHAPE,
     LAYER_MULADD,
@@ -68,6 +69,7 @@ public:
             case LAYER_ACTIVATION_CRELU:    return "ActivationCReLU";
             case LAYER_ACTIVATION_LEAKY:    return "ActivationLeaky";
             case LAYER_ACTIVATION_MISH:     return "ActivationMish";
+            case LAYER_ACTIVATION_LOGISTIC: return "ActivationLogistic";
             case LAYER_FLATTEN:             return "Flatten";
             case LAYER_RESHAPE:             return "Reshape";
             case LAYER_MULADD:              return "MulAdd";
@@ -212,7 +214,8 @@ public:
 typedef enum {
     ACTIVATION_ELU     = 100,
     ACTIVATION_LEAKY   = 101,
-    ACTIVATION_MISH   = 102
+    ACTIVATION_MISH   = 102,
+    ACTIVATION_LOGISTIC   = 103
 } tkdnnActivationMode_t;
 
 /**
@@ -233,6 +236,8 @@ public:
             return LAYER_ACTIVATION_LEAKY;
         else if (act_mode == ACTIVATION_MISH)
             return LAYER_ACTIVATION_MISH;
+        else if (act_mode == ACTIVATION_LOGISTIC)
+            return LAYER_ACTIVATION_LOGISTIC;
         else
             return LAYER_ACTIVATION;
          };

include/tkDNN/NetworkRT.h

@@ -24,6 +24,7 @@ template<typename T> T readBUF(const char*& buffer)
 
 using namespace nvinfer1;
 #include "pluginsRT/ActivationLeakyRT.h"
+#include "pluginsRT/ActivationLogisticRT.h"
 #include "pluginsRT/ActivationReLUCeilingRT.h"
 #include "pluginsRT/ActivationMishRT.h"
 #include "pluginsRT/ReorgRT.h"

include/tkDNN/pluginsRT/ActivationLogisticRT.h

@@ -0,0 +1,60 @@
+#include<cassert>
+#include "../kernels.h"
+
+class ActivationLogisticRT : public IPlugin {
+
+public:
+	ActivationLogisticRT() {
+
+
+	}
+
+	~ActivationLogisticRT(){
+
+	}
+
+	int getNbOutputs() const override {
+		return 1;
+	}
+
+	Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) override {
+		return inputs[0];
+	}
+
+	void configure(const Dims* inputDims, int nbInputs, const Dims* outputDims, int nbOutputs, int maxBatchSize) override {
+		size = 1;
+		for(int i=0; i<outputDims[0].nbDims; i++)
+			size *= outputDims[0].d[i];
+	}
+
+	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 {
+
+		activationLOGISTICForward((dnnType*)reinterpret_cast<const dnnType*>(inputs[0]), 
+											reinterpret_cast<dnnType*>(outputs[0]), batchSize*size, stream);
+		return 0;
+	}
+
+
+	virtual size_t getSerializationSize() override {
+		return 1*sizeof(int);
+	}
+
+	virtual void serialize(void* buffer) override {
+		char *buf = reinterpret_cast<char*>(buffer);
+		tk::dnn::writeBUF(buf, size);
+	}
+
+	int size;
+};

include/tkDNN/pluginsRT/YoloRT.h

@@ -67,15 +67,17 @@ public:
 		for (int b = 0; b < batchSize; ++b){
 			for(int n = 0; n < n_masks; ++n){
 				int index = entry_index(b, n*w*h, 0);
-				if (new_coords == 1)
-					activationLOGISTICForward(srcData + index, dstData + index, 4*w*h, stream); //x,y,w,h
-				else
+				if (new_coords == 1){
+					if (this->scaleXY != 1) scalAdd(dstData + index, 2 * w*h, this->scaleXY, -0.5*(this->scaleXY - 1), 1);
+				}
+				else{
 					activationLOGISTICForward(srcData + index, dstData + index, 2*w*h, stream); //x,y
 
-				if (this->scaleXY != 1) scalAdd(dstData + index, 2 * w*h, this->scaleXY, -0.5*(this->scaleXY - 1), 1);
+					if (this->scaleXY != 1) scalAdd(dstData + index, 2 * w*h, this->scaleXY, -0.5*(this->scaleXY - 1), 1);
 				
-				index = entry_index(b, n*w*h, 4);
-				activationLOGISTICForward(srcData + index, dstData + index, (1+classes)*w*h, stream);
+					index = entry_index(b, n*w*h, 4);
+					activationLOGISTICForward(srcData + index, dstData + index, (1+classes)*w*h, stream);
+				}
 			}
 		}