Add swish

src/Activation.cpp

@@ -52,6 +52,10 @@ dnnType* Activation::infer(dataDim_t &dim, dnnType* srcData) {
     else if(act_mode == ACTIVATION_MISH) {
         activationMishForward(srcData, dstData, dim.tot());
 
+    }
+    else if(act_mode == ACTIVATION_SWISH) {
+        activationSwishForward(srcData, dstData, dim.tot());
+
     }
     else if(act_mode == ACTIVATION_LOGISTIC) {
         activationLOGISTICForward(srcData, dstData, dim.tot());

src/DarknetParser.cpp

@@ -187,6 +187,7 @@ namespace tk { namespace dnn {
             if(f.activation == "relu") act = tkdnnActivationMode_t(CUDNN_ACTIVATION_RELU);
             else if(f.activation == "leaky") act = tk::dnn::ACTIVATION_LEAKY;
             else if(f.activation == "mish") act = tk::dnn::ACTIVATION_MISH;
+            else if(f.activation == "swish") act = tk::dnn::ACTIVATION_SWISH;
             else if(f.activation == "logistic") act = tk::dnn::ACTIVATION_LOGISTIC;
             else { FatalError("activation not supported: " + f.activation); }
             netLayers[netLayers.size()-1] = new tk::dnn::Activation(net, act);

src/NetworkRT.cpp

@@ -227,7 +227,7 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Layer *l) {
         return convert_layer(input, (Conv2d*) l);
     if(type == LAYER_POOLING)
         return convert_layer(input, (Pooling*) l);
-    if(type == LAYER_ACTIVATION || type == LAYER_ACTIVATION_CRELU || type == LAYER_ACTIVATION_LEAKY || type == LAYER_ACTIVATION_MISH || type == LAYER_ACTIVATION_LOGISTIC)
+    if(type == LAYER_ACTIVATION || type == LAYER_ACTIVATION_CRELU || type == LAYER_ACTIVATION_LEAKY || type == LAYER_ACTIVATION_MISH || type == LAYER_ACTIVATION_SWISH || type == LAYER_ACTIVATION_LOGISTIC)
         return convert_layer(input, (Activation*) l);
     if(type == LAYER_SOFTMAX)
         return convert_layer(input, (Softmax*) l);
@@ -424,6 +424,12 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Activation *l) {
         checkNULL(lRT);
         return lRT;
     }
+    else if(l->act_mode == ACTIVATION_SWISH) {
+        IPlugin *plugin = new ActivationSwishRT();
+        IPluginLayer *lRT = networkRT->addPlugin(&input, 1, *plugin);
+        checkNULL(lRT);
+        return lRT;
+    }
     else if(l->act_mode == ACTIVATION_LOGISTIC) {
         IPlugin *plugin = new ActivationLogisticRT();
         IPluginLayer *lRT = networkRT->addPlugin(&input, 1, *plugin);
@@ -674,6 +680,12 @@ IPlugin* PluginFactory::createPlugin(const char* layerName, const void* serialDa
         assert(buf == bufCheck + serialLength);
         return a;
     }
+    if(name.find("ActivationSwish") == 0) {
+        ActivationSwishRT *a = new ActivationSwishRT();
+        a->size = readBUF<int>(buf);
+        assert(buf == bufCheck + serialLength);
+        return a;
+    }
     if(name.find("ActivationLogistic") == 0) {
         ActivationLogisticRT *a = new ActivationLogisticRT();
         a->size = readBUF<int>(buf);

src/kernels/activation_swish.cu

@@ -0,0 +1,23 @@
+#include "kernels.h"
+
+__global__
+void activation_swish(dnnType *input, dnnType *output, int size) {
+
+    int i = blockDim.x*blockIdx.x + threadIdx.x;
+
+    if(i<size) {    
+        output[i] =  input[i] * 1.0f/(1.0f + exp(-input[i]));;
+    }
+ }
+
+
+/**
+    Swish activation function
+*/
+void activationSwishForward(dnnType* srcData, dnnType* dstData, int size, cudaStream_t stream)
+{
+    int blocks = (size+255)/256;
+    int threads = 256;
+    
+    activation_swish<<<blocks, threads, 0, stream>>>(srcData, dstData, size);
+}