Add yolo3_voc test

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

README.md

@@ -1,9 +1,9 @@
 # tkDNN
-tkDNN is a Deep Neural Network library built with cuDNN and tensorRT primitives, specifically thought to work on NVIDIA Jetson Boards. It has been tested on TK1(branch cudnn2), TX1, TX2, AGX Xavier and several discrete GPU.
+tkDNN is a Deep Neural Network library built with cuDNN and tensorRT primitives, specifically thought to work on NVIDIA Jetson Boards. It has been tested on TK1(branch cudnn2), TX1, TX2, AGX Xavier, Nano and several discrete GPUs.
 The main goal of this project is to exploit NVIDIA boards as much as possible to obtain the best inference performance. It does not allow training. 
 
 
-If you use tkDNN in your research, please cite one of the following papers. For use in commercial solutions, write at gattifrancesco@hotmail.it or refer to https://hipert.unimore.it/ .
+If you use tkDNN in your research, please cite one of the following papers. For use in commercial solutions, write at gattifrancesco@hotmail.it and micaela.verucchi@unimore.it or refer to https://hipert.unimore.it/ .
 
 ```
 Accepted paper @ IRC 2020, will soon be published.
@@ -175,15 +175,25 @@ All models from darknet are now parsed directly from cfg, you still need to expo
   mish
 </details>
 
-## Run the demo
+## Run the demo 
+This is an example using yolov4.
 
-To run the an object detection demo follow these steps (example with yolov3):
+To run the an object detection first create the .rt file by running:
 ```
-rm yolo3_fp32.rt        # be sure to delete(or move) old tensorRT files
-./test_yolo3            # run the yolo test (is slow)
-./demo yolo3_fp32.rt ../demo/yolo_test.mp4 y
+rm yolo4_fp32.rt        # be sure to delete(or move) old tensorRT files
+./test_yolo4            # run the yolo test (is slow)
 ```
-In general the demo program takes 4 parameters:
+If you get problems in the creation, try to check the error activating the debug of TensorRT in this way:
+```
+cmake .. -DDEBUG=True
+make
+```
+
+Once you have succesfully created your rt file, run the demo: 
+```
+./demo yolo4_fp32.rt ../demo/yolo_test.mp4 y
+```
+In general the demo program takes 6 parameters:
 ```
 ./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <n-batches> <show-flag>
 ```
@@ -197,6 +207,7 @@ where
 
 N.b. By default it is used FP32 inference
 
+
 ![demo](https://user-images.githubusercontent.com/11562617/72547657-540e7800-388d-11ea-83c6-49dfea2a0607.gif)
 
 ### FP16 inference

src/Conv2d.cpp

@@ -62,9 +62,10 @@ void Conv2d::initCUDNN(bool back) {
     // init workspace
     workSpace = NULL;
     ws_sizeInBytes = 0;
+    int algo_count = 0;
     if(back) {
         checkCUDNN( cudnnGetConvolutionBackwardDataAlgorithm_v7(net->cudnnHandle,
-                                                                filterDesc, dstTensor, convDesc, srcTensor, 1, 0, &bwAlgo) );
+                                                                filterDesc, dstTensor, convDesc, srcTensor, 1, &algo_count, &bwAlgo) );
         checkCUDNN(cudnnGetConvolutionBackwardDataWorkspaceSize(net->cudnnHandle,
                                                                 filterDesc, dstTensor, convDesc, srcTensor,
                                                                 bwAlgo.algo, &ws_sizeInBytes));
@@ -74,13 +75,17 @@ void Conv2d::initCUDNN(bool back) {
         srcTensorDesc = dstTensor;
         dstTensorDesc = srcTensor;
     } else {
+        
         checkCUDNN( cudnnGetConvolutionForwardAlgorithm_v7(net->cudnnHandle,
                                                          srcTensor, filterDesc, convDesc, dstTensor,
-                                                        1, 0, &algo) );
+                                                        1, &algo_count, &algo) );
          checkCUDNN(cudnnGetConvolutionForwardWorkspaceSize(net->cudnnHandle,
                                                             srcTensor, filterDesc, convDesc, dstTensor,
                                                            algo.algo, &ws_sizeInBytes));
     }
+
+    if(algo_count < 1)
+        FatalError("Cannot retrieve convolutional algo");
 }
 
 void Conv2d::inferCUDNN(dnnType* srcData, bool back) {

src/Yolo3Detection.cpp

@@ -113,34 +113,35 @@ void Yolo3Detection::postprocess(const int bi, const bool mAP){
         int x1   = (b.x+b.w/2.);
         int y0   = (b.y-b.h/2.);
         int y1   = (b.y+b.h/2.);
-        int obj_class = -1;
-        float prob = 0;
+
+        // convert to image coords
+        x0 = x_ratio*x0;
+        x1 = x_ratio*x1;
+        y0 = y_ratio*y0;
+        y1 = y_ratio*y1;
+        
         for(int c=0; c<classes; c++) {
             if(dets[j].prob[c] >= confThreshold) {
-                obj_class = c;
-                prob = dets[j].prob[c];
+                int obj_class = c;
+                float prob = dets[j].prob[c];
+
+                tk::dnn::box res;
+                res.cl = obj_class;
+                res.prob = prob;
+                res.x = x0;
+                res.y = y0;
+                res.w = x1 - x0;
+                res.h = y1 - y0;
+
+                // FIXME: this shuld be useless
+                // if(mAP)
+                //     for(int c=0; c<classes; c++) 
+                //         res.probs.push_back(dets[j].prob[c]);
+
+                detected.push_back(res);
             }
         }
 
-        if(obj_class >= 0) {
-            // convert to image coords
-            x0 = x_ratio*x0;
-            x1 = x_ratio*x1;
-            y0 = y_ratio*y0;
-            y1 = y_ratio*y1;
-              
-            tk::dnn::box res;
-            res.cl = obj_class;
-            res.prob = prob;
-            res.x = x0;
-            res.y = y0;
-            res.w = x1 - x0;
-            res.h = y1 - y0;
-            if(mAP)
-                for(int c=0; c<classes; c++) 
-                    res.probs.push_back(dets[j].prob[c]);
-            detected.push_back(res);
-        }
     }
     batchDetected.push_back(detected);
 }

tests/darknet/cfg/yolo3_voc.cfg

@@ -0,0 +1,785 @@
+[net]
+# Testing
+#  batch=1
+#  subdivisions=1
+# Training
+batch=64
+subdivisions=16
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 50200
+policy=steps
+steps=40000,45000
+scales=.1,.1
+
+
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+######################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=75
+activation=linear
+
+[yolo]
+mask = 6,7,8
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=20
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 61
+
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=75
+activation=linear
+
+[yolo]
+mask = 3,4,5
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=20
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 36
+
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=75
+activation=linear
+
+[yolo]
+mask = 0,1,2
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=20
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+

tests/darknet/yolo3_voc.cpp

@@ -0,0 +1,35 @@
+#include<iostream>
+#include<vector>
+#include "tkdnn.h"
+#include "test.h"
+#include "DarknetParser.h"
+
+int main() {
+    std::string bin_path  = "yolo3_voc";
+    std::vector<std::string> input_bins = { 
+        bin_path + "/layers/input.bin"
+    };
+    std::vector<std::string> output_bins = {
+	bin_path + "/debug/layer82_out.bin",
+        bin_path + "/debug/layer94_out.bin",
+        bin_path + "/debug/layer106_out.bin"
+    };
+    std::string wgs_path  = bin_path + "/layers";
+    std::string cfg_path  = std::string(TKDNN_PATH) + "/tests/darknet/cfg/yolo3_voc.cfg";
+    std::string name_path = std::string(TKDNN_PATH) + "/tests/darknet/names/voc.names";
+    downloadWeightsifDoNotExist(input_bins[0], bin_path, "https://cloud.hipert.unimore.it/s/mDJwCBgADc2xL4M/download");
+
+    // parse darknet network
+    tk::dnn::Network *net = tk::dnn::darknetParser(cfg_path, wgs_path, name_path);
+    net->print();
+
+    //convert network to tensorRT
+    tk::dnn::NetworkRT *netRT = new tk::dnn::NetworkRT(net, net->getNetworkRTName(bin_path.c_str()));
+    
+    int ret = testInference(input_bins, output_bins, net, netRT);
+    net->releaseLayers();
+    delete net;
+    delete netRT;
+    return ret;
+}
+