From 6d81473b2a6dab2652f8f72baeb07c8c7bcf285c Mon Sep 17 00:00:00 2001
From: Francesco Gatti <gattifrancesco@hotmail.it>
Date: Sat, 30 May 2020 22:11:00 +0200
Subject: [PATCH] yolo3 parsed ok

---
 include/tkDNN/DarknetParser.h |  8 +++++---
 tests/yolo3/yolo3.cpp         | 12 +++++-------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/tkDNN/DarknetParser.h b/include/tkDNN/DarknetParser.h
index 9a1a500..61040f9 100644
--- a/include/tkDNN/DarknetParser.h
+++ b/include/tkDNN/DarknetParser.h
@@ -140,15 +140,17 @@ namespace tk { namespace dnn {
         if(f.type == "convolutional") {
             std::string wgs = wgs_path + "/c" + std::to_string(netLayers.size()) + ".bin";
             printf("%d (%d,%d) (%d,%d) (%d,%d) %s %d %d\n", f.filters, f.size_x, f.size_y, f.stride_x, f.stride_y, f.padding_x, f.padding_y, wgs.c_str(), f.batch_normalize, f.groups);
-            netLayers.push_back(new tk::dnn::Conv2d(net, f.filters, f.size_x, f.size_y, f.stride_x, 
-                                f.stride_y, f.padding_x, f.padding_y, wgs, f.batch_normalize, false, f.groups));
+            tk::dnn::Conv2d *l= new tk::dnn::Conv2d(net, f.filters, f.size_x, f.size_y, f.stride_x, 
+                                f.stride_y, f.padding_x, f.padding_y, wgs, f.batch_normalize, false, f.groups);
             if(f.activation != "linear") {
                 tkdnnActivationMode_t act;
                 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 { FatalError("activation not supported: " + f.activation); }
-                new tk::dnn::Activation(net, act);
+                netLayers.push_back(new tk::dnn::Activation(net, act));
+            } else {
+                netLayers.push_back(l);
             }
         } else if(f.type == "shortcut") {
             if(f.layers.size() != 1) FatalError("no layers to shortcut\n");
diff --git a/tests/yolo3/yolo3.cpp b/tests/yolo3/yolo3.cpp
index 70f0b9f..1036261 100644
--- a/tests/yolo3/yolo3.cpp
+++ b/tests/yolo3/yolo3.cpp
@@ -12,7 +12,6 @@ int main() {
     tk::dnn::Network *net = tk::dnn::darknetParser("../tests/yolo3/yolov3.cfg", "yolo3/layers");
     net->print();
 
-    
     std::vector<tk::dnn::Yolo*> yolo;
     for(int i=0; i<net->num_layers; i++) {
         if(net->layers[i]->getLayerType() == tk::dnn::layerType_t::LAYER_YOLO)
@@ -24,6 +23,10 @@ int main() {
         yolo[i]->classesNames = {"person" , "bicycle" , "car" , "motorbike" , "aeroplane" , "bus" , "train" , "truck" , "boat" , "traffic light" , "fire hydrant" , "stop sign" , "parking meter" , "bench" , "bird" , "cat" , "dog" , "horse" , "sheep" , "cow" , "elephant" , "bear" , "zebra" , "giraffe" , "backpack" , "umbrella" , "handbag" , "tie" , "suitcase" , "frisbee" , "skis" , "snowboard" , "sports ball" , "kite" , "baseball bat" , "baseball glove" , "skateboard" , "surfboard" , "tennis racket" , "bottle" , "wine glass" , "cup" , "fork" , "knife" , "spoon" , "bowl" , "banana" , "apple" , "sandwich" , "orange" , "broccoli" , "carrot" , "hot dog" , "pizza" , "donut" , "cake" , "chair" , "sofa" , "pottedplant" , "bed" , "diningtable" , "toilet" , "tvmonitor" , "laptop" , "mouse" , "remote" , "keyboard" , "cell phone" , "microwave" , "oven" , "toaster" , "sink" , "refrigerator" , "book" , "clock" , "vase" , "scissors" , "teddy bear" , "hair drier" , "toothbrush"};
     }
 
+    //convert network to tensorRT
+    tk::dnn::NetworkRT netRT(net, net->getNetworkRTName("yolo3"));
+    
+
     std::string input_bin = bin_path + "/layers/input.bin";
     std::vector<std::string> output_bins = {
         bin_path + "/debug/layer82_out.bin",
@@ -36,16 +39,12 @@ int main() {
     dnnType *input_h;
     readBinaryFile(input_bin, net->input_dim.tot(), &input_h, &data);
 
-    
-    //convert network to tensorRT
-    tk::dnn::NetworkRT netRT(net, net->getNetworkRTName("yolo3"));
-    
     // the network have 3 outputs
     tk::dnn::dataDim_t out_dim[3];
     for(int i=0; i<3; i++) out_dim[i] = yolo[i]->output_dim; 
     dnnType *cudnn_out[3], *rt_out[3]; 
 
-    tk::dnn::dataDim_t dim1 = net->input_dim; //input dim
+    tk::dnn::dataDim_t dim1 =  net->input_dim; //input dim
     printCenteredTitle(" CUDNN inference ", '=', 30); {
         dim1.print();
         TIMER_START
@@ -80,5 +79,4 @@ int main() {
         ret_cudnn_tensorrt |= checkResult(odim, cudnn_out[i], rt_out[i]) == 0 ? 0 : ERROR_CUDNNvsTENSORRT;
     }
     return ret_cudnn | ret_tensorrt | ret_cudnn_tensorrt;
-    
 }