mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Merge remote-tracking branch 'origin/master' into cnet

Browse Source 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
This commit is contained in:
Davide Sapienza
2020-12-07 17:45:44 +01:00
parent 3d2405323b b8855b9599
commit 7f65ee0b2a
138 changed files with 6667 additions and 5411 deletions
Download Patch File Download Diff File Expand all files Collapse all files
demo/config.yaml
+1 -1
View File
@@ -3,5 +3,5 @@ map_points : 101 #number of recall points (0 for all, 101 for COCO, 11 Pascal
map_levels : 10 #number of IoU step for the AP
map_step : 0.05 #step of IoU
IoU_thresh : 0.5 #starting IoU threshold
conf_thresh : 0.0 #threshold on the condifence of the bbox
conf_thresh : 0.001 #threshold on the condifence of the bbox
verbose : false #print on screen information
demo/demo/demo.cpp
+49 -21
View File
@@ -34,6 +34,21 @@ int main(int argc, char *argv[]) {
int n_classes = 80;
if(argc > 4)
n_classes = atoi(argv[4]);
int n_batch = 1;
if(argc > 5)
n_batch = atoi(argv[5]);
bool show = true;
if(argc > 6)
show = atoi(argv[6]);
float conf_thresh=0.3;
if(argc > 7)
conf_thresh = atof(argv[7]);
if(n_batch < 1 || n_batch > 64)
FatalError("Batch dim not supported");
if(!show)
SAVE_RESULT = true;
tk::dnn::Yolo3Detection yolo;
tk::dnn::CenternetDetection cnet;
@@ -57,7 +72,7 @@ int main(int argc, char *argv[]) {
FatalError("Network type not allowed (3rd parameter)\n");
}
detNN->init(net, n_classes);
detNN->init(net, n_classes, n_batch, conf_thresh);
gRun = true;
@@ -75,27 +90,40 @@ int main(int argc, char *argv[]) {
}
cv::Mat frame;
cv::Mat dnn_input;
cv::namedWindow("detection", cv::WINDOW_NORMAL);
std::vector<tk::dnn::box> detected_bbox;
if(show)
cv::namedWindow("detection", cv::WINDOW_NORMAL);
std::vector<cv::Mat> batch_frame;
std::vector<cv::Mat> batch_dnn_input;
while(gRun) {
cap >> frame;
if(!frame.data) {
break;
}
// this will be resized to the net format
dnn_input = frame.clone();
batch_dnn_input.clear();
batch_frame.clear();
//inference
detNN->update(dnn_input);
frame = detNN->draw(frame);
for(int bi=0; bi< n_batch; ++bi){
cap >> frame;
if(!frame.data)
break;
batch_frame.push_back(frame);
cv::imshow("detection", frame);
cv::waitKey(1);
if(SAVE_RESULT)
// this will be resized to the net format
batch_dnn_input.push_back(frame.clone());
}
if(!frame.data)
break;
//inference
detNN->update(batch_dnn_input, n_batch);
detNN->draw(batch_frame);
if(show){
for(int bi=0; bi< n_batch; ++bi){
cv::imshow("detection", batch_frame[bi]);
cv::waitKey(1);
}
}
if(n_batch == 1 && SAVE_RESULT)
resultVideo << frame;
}
@@ -103,10 +131,10 @@ int main(int argc, char *argv[]) {
double mean = 0;
std::cout<<COL_GREENB<<"\n\nTime stats:\n";
std::cout<<"Min: "<<*std::min_element(detNN->stats.begin(), detNN->stats.end())<<" ms\n";
std::cout<<"Max: "<<*std::max_element(detNN->stats.begin(), detNN->stats.end())<<" ms\n";
std::cout<<"Min: "<<*std::min_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n";
std::cout<<"Max: "<<*std::max_element(detNN->stats.begin(), detNN->stats.end())/n_batch<<" ms\n";
for(int i=0; i<detNN->stats.size(); i++) mean += detNN->stats[i]; mean /= detNN->stats.size();
std::cout<<"Avg: "<<mean<<" ms\n"<<COL_END;
std::cout<<"Avg: "<<mean/n_batch<<" ms\t"<<1000/(mean/n_batch)<<" FPS\n"<<COL_END;
return 0;
demo/demo/map.cpp
+49 -27
View File
@@ -34,6 +34,7 @@ int main(int argc, char *argv[])
bool show = false;
bool write_dets = false;
bool write_res_on_file = true;
bool write_coco_json = true;
int n_images = 5000;
bool verbose;
@@ -43,6 +44,7 @@ int main(int argc, char *argv[])
double vm_total = 0, rss_total = 0;
double vm, rss;
//read args
if(argc > 1)
net = argv[1];
if(argc > 2)
@@ -52,6 +54,7 @@ int main(int argc, char *argv[])
if(argc > 4)
config_filename = argv[4];
//check if files needed exist
if(!fileExist(config_filename))
FatalError("Wrong config file path.");
if(!fileExist(net))
@@ -63,26 +66,31 @@ int main(int argc, char *argv[])
tk::dnn::readmAPParams( config_filename, classes, map_points, map_levels, map_step,
IoU_thresh, conf_thresh, verbose);
std::ofstream times, memory;
//extract network name from rt path
std::string net_name;
removePathAndExtension(net, net_name);
std::cout<<"Network: "<<net_name<<std::endl;
//open files (if needed)
std::ofstream times, memory, coco_json;
if(write_coco_json){
coco_json.open(net_name+"_COCO_res.json");
coco_json << "[\n";
}
if(write_res_on_file){
times.open("times_"+net_name+".csv");
memory.open("memory.csv", std::ios_base::app);
memory<<net<<";";
}
// instantiate detector
tk::dnn::Yolo3Detection yolo;
tk::dnn::CenternetDetection cnet;
tk::dnn::MobilenetDetection mbnet;
tk::dnn::DetectionNN *detNN;
int n_classes = classes;
switch(ntype){
case 'y':
detNN = &yolo;
@@ -97,9 +105,9 @@ int main(int argc, char *argv[])
default:
FatalError("Network type not allowed (3rd parameter)\n");
}
detNN->init(net, n_classes, 1, conf_thresh);
detNN->init(net, n_classes);
//read images
std::ifstream all_labels(labels_path);
std::string l_filename;
std::vector<tk::dnn::Frame> images;
@@ -124,24 +132,28 @@ int main(int argc, char *argv[])
FatalError("Wrong image file path.");
cv::Mat frame = cv::imread(f.iFilename.c_str(), cv::IMREAD_COLOR);
std::vector<cv::Mat> batch_frames;
batch_frames.push_back(frame);
int height = frame.rows;
int width = frame.cols;
cv::Mat dnn_input;
if(!frame.data)
break;
dnn_input = frame.clone();
std::vector<cv::Mat> batch_dnn_input;
batch_dnn_input.push_back(frame.clone());
//inference
detected_bbox.clear();
detNN->update(dnn_input, write_res_on_file, &times);
frame = detNN->draw(frame);
detNN->update(batch_dnn_input,1,write_res_on_file, &times, write_coco_json);
detNN->draw(batch_frames);
detected_bbox = detNN->detected;
if(write_coco_json)
printJsonCOCOFormat(&coco_json, f.iFilename.c_str(), detected_bbox, classes, width, height);
std::ofstream myfile;
if(write_dets)
myfile.open ("det/"+f.lFilename.substr(f.lFilename.find("000")));
myfile.open ("det/"+f.lFilename.substr(f.lFilename.find("labels/") + 7));
// save detections labels
for(auto d:detected_bbox){
@@ -157,33 +169,36 @@ int main(int argc, char *argv[])
f.det.push_back(b);
if(write_dets)
myfile << d.cl << " "<< d.prob << " "<< d.x << " "<< d.y << " "<< d.w << " "<< d.h <<"\n";
myfile << d.cl << " "<< d.prob << " "<< b.x << " "<< b.y << " "<< b.w << " "<< b.h <<"\n";
if(show)// draw rectangle for detection
cv::rectangle(frame, cv::Point(d.x, d.y), cv::Point(d.x + d.w, d.y + d.h), cv::Scalar(0, 0, 255), 2);
cv::rectangle(batch_frames[0], cv::Point(d.x, d.y), cv::Point(d.x + d.w, d.y + d.h), cv::Scalar(0, 0, 255), 2);
}
if(write_dets)
myfile.close();
// read and save groundtruth labels
std::ifstream labels(l_filename);
for(std::string line; std::getline(labels, line); ){
std::istringstream in(line);
tk::dnn::BoundingBox b;
in >> b.cl >> b.x >> b.y >> b.w >> b.h;
b.prob = 1;
b.truthFlag = 1;
f.gt.push_back(b);
if(fileExist(f.lFilename.c_str()))
{
std::ifstream labels(l_filename);
for(std::string line; std::getline(labels, line); ){
std::istringstream in(line);
tk::dnn::BoundingBox b;
in >> b.cl >> b.x >> b.y >> b.w >> b.h;
b.prob = 1;
b.truthFlag = 1;
f.gt.push_back(b);
if(show)// draw rectangle for groundtruth
cv::rectangle(frame, cv::Point((b.x-b.w/2)*width, (b.y-b.h/2)*height), cv::Point((b.x+b.w/2)*width,(b.y+b.h/2)*height), cv::Scalar(0, 255, 0), 2);
if(show)// draw rectangle for groundtruth
cv::rectangle(batch_frames[0], cv::Point((b.x-b.w/2)*width, (b.y-b.h/2)*height), cv::Point((b.x+b.w/2)*width,(b.y+b.h/2)*height), cv::Scalar(0, 255, 0), 2);
}
}
images.push_back(f);
if(show){
cv::imshow("detection", frame);
cv::imshow("detection", batch_frames[0]);
cv::waitKey(0);
}
@@ -193,6 +208,13 @@ int main(int argc, char *argv[])
}
if(write_coco_json){
coco_json.seekp (coco_json.tellp() - std::streampos(2));
coco_json << "\n]\n";
coco_json.close();
}
std::cout << "Avg VM[MB]: " << vm_total/images_done/1024.0 << ";Avg RSS[MB]: " << rss_total/images_done/1024.0 << std::endl;
//compute mAP