yolo

opencv-yolo/Makefile

@@ -3,7 +3,7 @@ CFLAGS = -g -Wall -std=c++11
 SRCS = main.cpp
 PROG = main
 
-OPENCV = `pkg-config opencv --cflags --libs`
+OPENCV = `pkg-config opencv4 --cflags --libs`
 LIBS = $(OPENCV)
 
 $(PROG):$(SRCS)

opencv-yolo/coco.names.txt

+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

opencv-yolo/main.cpp

@@ -33,7 +33,7 @@ int inpHeight = 416; // Height of network's input image
 vector<string> classes;
 
 // Remove the bounding boxes with low confidence using non-maxima suppression
-void postprocess(Mat& frame, const vector<Mat>& out);
+int postprocess(Mat& frame, const vector<Mat>& out);
 
 // Draw the predicted bounding box
 void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
@@ -80,8 +80,8 @@ int main(int argc, char** argv)
             ifstream ifile(str);
             if (!ifile) throw("error");
             cap.open(str);
-            //str.replace(str.end()-4, str.end(), "_yolo_out_cpp.jpg");
-            //outputFile = str;
+            str.replace(str.end()-4, str.end(), "_yolo_out_cpp"); //.jpg
+            outputFile = str;
         }
         else if (parser.has("video"))
         {
@@ -93,11 +93,12 @@ int main(int argc, char** argv)
             if(!cap.open(str)){
                 cout << "failed to open video stream: " << str << endl;
             }
-            //str.replace(str.end()-4, str.end(), "_yolo_out_cpp.avi");
-            //outputFile = str;
-        }
+            str.replace(str.end()-4, str.end(), "_yolo_out_cpp.avi");
+        }else{
             // Open the webcaom
-        else cap.open(parser.get<int>("device"));
+            cap.open(parser.get<int>("device"));
+        }
+
         cout << "output file: " << outputFile << endl;
         
     }
@@ -117,7 +118,7 @@ int main(int argc, char** argv)
 
     // Process frames.
     long frameCnt = 0;
-    
+    long detCnt = 0;
     while (waitKey(1) < 0)
     {
         // get frame from the video
@@ -147,7 +148,10 @@ int main(int argc, char** argv)
         net.forward(outs, getOutputsNames(net));
         
         // Remove the bounding boxes with low confidence
-        postprocess(frame, outs);
+        int numDet = postprocess(frame, outs);
+        if(numDet == 0 && parser.has("image")) {
+            continue;
+        }
         
         // Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
         vector<double> layersTimes;
@@ -159,7 +163,11 @@ int main(int argc, char** argv)
         // Write the frame with the detection boxes
         Mat detectedFrame;
         frame.convertTo(detectedFrame, CV_8U);
-        if (parser.has("image")) imwrite(outputFile, detectedFrame);
+        if (parser.has("image")) {
+            string ofname = outputFile + to_string(detCnt) + ".jpg";
+            imwrite(ofname, detectedFrame);
+            detCnt++;
+        }
         else {
             video.write(detectedFrame);
         }    
@@ -173,7 +181,7 @@ int main(int argc, char** argv)
 }
 
 // Remove the bounding boxes with low confidence using non-maxima suppression
-void postprocess(Mat& frame, const vector<Mat>& outs)
+int postprocess(Mat& frame, const vector<Mat>& outs)
 {
     vector<int> classIds;
     vector<float> confidences;
@@ -219,6 +227,8 @@ void postprocess(Mat& frame, const vector<Mat>& outs)
         drawPred(classIds[idx], confidences[idx], box.x, box.y,
                  box.x + box.width, box.y + box.height, frame);
     }
+
+    return indices.size();
 }
 
 // Draw the predicted bounding box

opencv-yolo/yolov3-tiny.cfg

+[net]
+# Testing
+batch=1
+subdivisions=1
+# Training
+# batch=64
+# subdivisions=2
+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 = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=1
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+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
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+
+[yolo]
+mask = 3,4,5
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+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, 8
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+[yolo]
+mask = 0,1,2
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1