diff --git a/CMakeLists.txt b/CMakeLists.txt
index 13db7b5..c29e987 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -5,6 +5,10 @@ set(CMAKE_CXX_STANDARD 14)
option(ENABLE_OPENCV_CUDA_CONTRIB "Enable OpenCV CUDA Contrib" OFF )
+if(NOT CMAKE_BUILD_TYPE)
+ set(CMAKE_BUILD_TYPE "Release" CACHE STRING "default build" FORCE)
+endif(NOT CMAKE_BUILD_TYPE)
+
find_package(CUDA 9.0 REQUIRED)
if (CUDA_FOUND)
set(OUTPUTFILE ${CMAKE_CURRENT_SOURCE_DIR}/cmake/cuda_script) # No suffix required
@@ -202,12 +206,17 @@ target_link_libraries(test_shelfnet_berkeley tkDNN)
add_executable(test_shelfnet_mapillary tests/shelfnet/shelfnet_mapillary.cpp)
target_link_libraries(test_shelfnet_mapillary tkDNN)
+add_executable(test_shelfnet_coco tests/shelfnet/shelfnet_coco.cpp)
+target_link_libraries(test_shelfnet_coco tkDNN)
+
# MONODEPTH2
add_executable(test_monodepth2_640 tests/monodepth2/monodepth2_640.cpp)
target_link_libraries(test_monodepth2_640 tkDNN)
add_executable(test_monodepth2_1024 tests/monodepth2/monodepth2_1024.cpp)
target_link_libraries(test_monodepth2_1024 tkDNN)
+
+
# DEMOS
add_executable(test_rtinference tests/test_rtinference/rtinference.cpp)
target_link_libraries(test_rtinference tkDNN)
diff --git a/README.md b/README.md
index fa00681..825c00b 100644
--- a/README.md
+++ b/README.md
@@ -23,12 +23,11 @@ If you use tkDNN in your research, please cite the [following paper](https://iee
- [x] Support 2D/3D Object Detection and Tracking [README](docs/README_2d3dtracking.md)
#### 24 November 2021
- [x] Support to sematic segmentation on cuda 11
-- [x] Support to TensorRT8 (tensort8 branch).
-
+- [x] Support to TensorRT8. (thanks to [Harshvardhan Chandirasekar](https://github.com/perseusdg))
#### 30 March 2022
-- [x] Support to monocular depth esitmation (tensort8 branch) [README](docs/README_depth.md)
+- [x] Support to monocular depth esitmation [README](docs/README_depth.md) (thanks to [Harshvardhan Chandirasekar](https://github.com/perseusdg))
+
-TensorRT8 (and therefore Jetpack 4.6) is currently supported only on the branch tensort8 due to [performance issue with TensorRT8](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html)). We will merge it to the master as soon as those issues are fixed (probably in future minor releases).
## FPS Results
Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimension as the input size, on
@@ -120,8 +119,8 @@ git clone https://github.com/ceccocats/tkDNN
cd tkDNN
mkdir build
cd build
-cmake -DCMAKE_BUILD_TYPE=Release -G"Ninja" ..
-ninja
+cmake -DCMAKE_BUILD_TYPE=Release ..
+make
```
## Workflow
@@ -179,11 +178,10 @@ For specific details on how to run tkDNN on Windows 10/11 see [HERE](./docs/wind
| yolo4_320 | Yolov4 8 | [COCO 2017](http://cocodataset.org/) | 80 | 320x320 | [weights](https://cloud.hipert.unimore.it/s/d97CFzYqCPCp5Hg/download) |
| yolo4_512 | Yolov4 8 | [COCO 2017](http://cocodataset.org/) | 80 | 512x512 | [weights](https://cloud.hipert.unimore.it/s/d97CFzYqCPCp5Hg/download) |
| yolo4_608 | Yolov4 8 | [COCO 2017](http://cocodataset.org/) | 80 | 608x608 | [weights](https://cloud.hipert.unimore.it/s/d97CFzYqCPCp5Hg/download) |
-| yolo4_berkeley | Yolov4 8 | [BDD100K ](https://bair.berkeley.edu/blog/2018/05/30/bdd/) | 10 | 540x320 | [weights](https://cloud.hipert.unimore.it/s/nkWFa5fgb4NTdnB/download) |
+| yolo4_berkeley | Yolov4 8 | [BDD100K ](https://bair.berkeley.edu/blog/2018/05/30/bdd/) | 10 | 544x320 | [weights](https://cloud.hipert.unimore.it/s/nkWFa5fgb4NTdnB/download) |
| yolo4tiny | Yolov4 tiny 9 | [COCO 2017](http://cocodataset.org/) | 80 | 416x416 | [weights](https://cloud.hipert.unimore.it/s/iRnc4pSqmx78gJs/download) |
-| yolo4x | Yolov4x-mish 9 | [COCO 2017](http://cocodataset.org/) |
+| yolo4x | Yolov4x-mish 9 | [COCO 2017](http://cocodataset.org/) | 80 | 640x640 | [weights](https://cloud.hipert.unimore.it/s/5MFjtNtgbDGdJEo/download) |
| yolo4tiny_512 | Yolov4 tiny 9 | [COCO 2017](http://cocodataset.org/) | 80 | 512x512 | [weights](https://cloud.hipert.unimore.it/s/iRnc4pSqmx78gJs/download) |
-80 | 640x640 | [weights](https://cloud.hipert.unimore.it/s/5MFjtNtgbDGdJEo/download) |
| yolo4x-cps | Scaled Yolov4 10 | [COCO 2017](http://cocodataset.org/) | 80 | 512x512 | [weights](https://cloud.hipert.unimore.it/s/AfzHE4BfTeEm2gH/download) |
| shelfnet | ShelfNet18_realtime11 | [Cityscapes](https://www.cityscapes-dataset.com/) | 19 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/mEDZMRJaGCFWSJF/download) |
| shelfnet_berkeley | ShelfNet18_realtime11 | [DeepDrive](https://bdd-data.berkeley.edu/) | 20 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/m92e7QdD9gYMF7f/download) |
diff --git a/demo/demo/demo.cpp b/demo/demo/demo.cpp
index f46ca80..c857086 100644
--- a/demo/demo/demo.cpp
+++ b/demo/demo/demo.cpp
@@ -9,7 +9,6 @@
#include "Yolo3Detection.h"
bool gRun;
-bool SAVE_RESULT = false;
void sig_handler(int signo) {
std::cout<<"request gateway stop\n";
@@ -20,44 +19,41 @@ int main(int argc, char *argv[]) {
signal(SIGINT, sig_handler);
-#ifdef __linux__
- std::string config_file = "../demo/demoConfig.yaml";
-#elif _WIN32
- std::string config_file = "..\\..\\..\\demo\\demoConfig.yaml";
-#endif
-
- if(argc > 1){
- config_file = argv[1];
- }
-
- YAML::Node conf = YAMLloadConf(config_file);
- if(!conf){
+ // get config file path and read it
+ #ifdef __linux__
+ std::string config_file = "../demo/demoConfig.yaml";
+ #elif _WIN32
+ std::string config_file = "..\\..\\..\\demo\\demoConfig.yaml";
+ #endif
+ if(argc > 1)
+ config_file = argv[1];
+
+ YAML::Node conf = YAMLloadConf(config_file);
+ if(!conf)
FatalError("Problem with config file");
- }
-
- std::string net = YAMLgetConf(conf,"net","yolo4tiny_fp32.rt");
- if(!fileExist(net.c_str())) {
+ // read settings from config file
+ std::string net = YAMLgetConf(conf, "net", "yolo4tiny_fp32.rt");
+ if(!fileExist(net.c_str()))
FatalError("The given network does not exist. Create the rt first.");
- }
-#ifdef __linux__
- std::string input = YAMLgetConf(conf, "input", "../demo/yolo_test.mp4");
- std::string cfgPath = YAMLgetConf(conf,"cfg_input", "../tests/darknet/cfg/yolo4tiny.cfg");
- std::string namePath = YAMLgetConf(conf,"name_input","../tests/darknet/names/coco.names");
-#elif _WIN32
- std::string input = YAMLgetConf(conf, "win_input", "..\\..\\..\\demo\\yolo_test.mp4");
- std::string cfgPath = YAMLgetConf(conf,"cfg_win_input","..\\..\\..\\tests\\darknet\\cfg\\yolo4tiny.cfg");
- std::string namePath = YAMLgetConf(conf,"name_win_input","..\\..\\..\\tests\\darknet\\names\\coco.names");
-#endif
- if(!fileExist(input.c_str()))
- FatalError("The given input video does not exist.");
+ #ifdef __linux__
+ std::string input = YAMLgetConf(conf, "input", "../demo/yolo_test.mp4");
+ std::string cfgPath = YAMLgetConf(conf,"cfg_input", "../tests/darknet/cfg/yolo4tiny.cfg");
+ std::string namePath = YAMLgetConf(conf,"name_input","../tests/darknet/names/coco.names");
+ #elif _WIN32
+ std::string input = YAMLgetConf(conf, "win_input", "..\\..\\..\\demo\\yolo_test.mp4");
+ std::string cfgPath = YAMLgetConf(conf,"cfg_win_input","..\\..\\..\\tests\\darknet\\cfg\\yolo4tiny.cfg");
+ std::string namePath = YAMLgetConf(conf,"name_win_input","..\\..\\..\\tests\\darknet\\names\\coco.names");
+ #endif
+ if(!fileExist(input.c_str()))
+ FatalError("The given input video does not exist.");
char ntype = YAMLgetConf(conf, "ntype", 'y');
int n_classes = YAMLgetConf(conf, "n_classes", 80);
int n_batch = YAMLgetConf(conf, "n_batch", 1);
if(n_batch < 1 || n_batch > 64)
- FatalError("Batch dim not supported");
+ FatalError("Batch dim not supported");
float conf_thresh = YAMLgetConf(conf, "conf_thresh", 0.3);
bool show = YAMLgetConf(conf, "show", true);
bool save = YAMLgetConf(conf, "save", false);
@@ -70,7 +66,8 @@ int main(int argc, char *argv[]) {
std::cout <<"Demo settings - input: "<< input
<<", show: "<< show
<<", save: "<< save<<"\n\n";
-
+
+ // create detection network
tk::dnn::Yolo3Detection yolo;
tk::dnn::CenternetDetection cnet;
tk::dnn::MobilenetDetection mbnet;
@@ -100,8 +97,7 @@ int main(int argc, char *argv[]) {
detNN->init(net,cfgPath,namePath,n_classes,n_batch,conf_thresh);
- gRun = true;
-
+ // open video stream
cv::VideoCapture cap(input);
if(!cap.isOpened())
gRun = false;
@@ -115,13 +111,15 @@ int main(int argc, char *argv[]) {
resultVideo.open("result.mp4", cv::VideoWriter::fourcc('M','P','4','V'), 30, cv::Size(w, h));
}
- cv::Mat frame;
if(show)
cv::namedWindow("detection", cv::WINDOW_NORMAL);
+ cv::Mat frame;
std::vector batch_frame;
std::vector batch_dnn_input;
+ // start detection loop
+ gRun = true;
while(gRun) {
batch_dnn_input.clear();
batch_frame.clear();
@@ -154,14 +152,13 @@ int main(int argc, char *argv[]) {
}
std::cout<<"detection end\n";
+
double mean = 0;
-
std::cout<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";
+ 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";
for(int i=0; istats.size(); i++) mean += detNN->stats[i]; mean /= detNN->stats.size();
- std::cout<<"Avg: "<stream));
return true;
+ return true;
}
/**
diff --git a/include/tkDNN/utils.h b/include/tkDNN/utils.h
index a1a1f1c..055ea67 100644
--- a/include/tkDNN/utils.h
+++ b/include/tkDNN/utils.h
@@ -23,6 +23,7 @@
#include
#include
+#include
@@ -176,5 +177,4 @@ inline T YAMLgetConf(YAML::Node conf, std::string key, T defaultVal) {
return val;
}
-
#endif //UTILS_H
diff --git a/scripts/test_all_tests.sh b/scripts/test_all_tests.sh
index 0da9b6b..e44f7e8 100644
--- a/scripts/test_all_tests.sh
+++ b/scripts/test_all_tests.sh
@@ -1,6 +1,6 @@
#!/bin/bash
-cd build
+#cd build
RED='\033[1;31m'
GREEN='\033[1;32m'
@@ -29,24 +29,28 @@ function print_output {
}
+out_dir=results
out_file=results.log
-rm $out_file
+rm -rf $out_dir/
+mkdir -p $out_dir
function test_net {
- ./test_$1 &>> $out_file
+ ./test_$1 &> $out_dir/$1_${TKDNN_MODE}_build_$out_file
print_output $? $1
- ./test_rtinference $1*.rt $TKDNN_BATCHSIZE &>> $out_file
+ ./test_rtinference $1*.rt 1 &> $out_dir/$1_${TKDNN_MODE}_inference_batch1_$out_file
+ print_output $? "infer $1"
+ ./test_rtinference $1*.rt $TKDNN_BATCHSIZE &> $out_dir/$1_${TKDNN_MODE}_inference_batch${TKDNN_BATCHSIZE}_$out_file
print_output $? "batched $1"
}
-modes=( 1 ) # only FP32
-# modes=( 1 2 ) # FP32 and FP16
+# modes=( 1 ) # only FP32
+modes=( 1 2 ) # FP32 and FP16
# modes=( 1 2 3 ) # FP32, FP16 and INT8
for i in "${modes[@]}"
do
- rm *rt
+ rm -f *rt
if [ $i -eq 1 ]
then
export TKDNN_MODE=FP32
@@ -73,37 +77,37 @@ do
# print_output $? imuodom
test_net yolo4
- test_net yolo4_320
- test_net yolo4_320_coco2
- test_net yolo4_512
- test_net yolo4_608
- test_net yolo4-csp
- test_net yolo4x
- test_net yolo4_berkeley
- test_net yolo4_berkeley_f1
- test_net yolo4tiny
- test_net yolo4tiny_512
- test_net yolo3
- test_net yolo3_berkeley
- test_net yolo3_coco4
- test_net yolo3_flir
- test_net yolo3_512
- test_net yolo3tiny
- test_net yolo3tiny_512
- test_net yolo2
- test_net yolo2_voc
- #test_net yolo2tiny
- test_net csresnext50-panet-spp
- #test_net csresnext50-panet-spp_berkeley
- test_net resnet101_cnet
- test_net dla34_cnet
- test_net dla34_cnet3d
- test_net mobilenetv2ssd
- test_net mobilenetv2ssd512
- test_net bdd-mobilenetv2ssd
- test_net dla34_ctrack
- test_net shelfnet
- test_net shelfnet_berkeley
+ # test_net yolo4_320
+ # test_net yolo4_320_coco2
+ # test_net yolo4_512
+ # test_net yolo4_608
+ # test_net yolo4-csp
+ # test_net yolo4x
+ # test_net yolo4_berkeley
+ # test_net yolo4_berkeley_f1
+ # test_net yolo4tiny
+ # test_net yolo4tiny_512
+ # test_net yolo3
+ # test_net yolo3_berkeley
+ # test_net yolo3_coco4
+ # test_net yolo3_flir
+ # test_net yolo3_512
+ # test_net yolo3tiny
+ # test_net yolo3tiny_512
+ # test_net yolo2
+ # test_net yolo2_voc
+ # test_net yolo2tiny
+ # test_net csresnext50-panet-spp
+ # test_net csresnext50-panet-spp_berkeley
+ # test_net resnet101_cnet
+ # test_net dla34_cnet
+ # test_net dla34_cnet3d
+ # test_net mobilenetv2ssd
+ # test_net mobilenetv2ssd512
+ # test_net bdd-mobilenetv2ssd
+ # test_net dla34_ctrack
+ # test_net shelfnet
+ # test_net shelfnet_berkeley
done
-echo "If errors occured, check logfile $out_file"
+echo "If errors occured, check logfiles in directory: $out_dir"
diff --git a/src/CenternetDetection.cpp b/src/CenternetDetection.cpp
index 133c682..eba8ce4 100644
--- a/src/CenternetDetection.cpp
+++ b/src/CenternetDetection.cpp
@@ -120,6 +120,7 @@ bool CenternetDetection::init(const std::string& tensor_path, const std::string&
dst2.at(2,1)=dst2.at(1,1) + (dst2.at(0,0)-dst2.at(1,0) );
return true;
+ return true;
}
diff --git a/src/MobilenetDetection.cpp b/src/MobilenetDetection.cpp
index 1d3832d..94c90c7 100644
--- a/src/MobilenetDetection.cpp
+++ b/src/MobilenetDetection.cpp
@@ -198,7 +198,7 @@ bool MobilenetDetection::init(const std::string& tensor_path, const std::string&
"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" ,
+ "toilet" , "tvmonitor" , "laptop" , "mouse" , "remote" , "keyboard" ,
"cell phone" , "microwave" , "oven" , "toaster" , "sink" , "refrigerator" ,
"book" , "clock" , "vase" , "scissors" , "teddy bear" , "hair drier" , "toothbrush"};
classesNames = std::vector(classes_names_, std::end(classes_names_));
@@ -207,7 +207,7 @@ bool MobilenetDetection::init(const std::string& tensor_path, const std::string&
else{
FatalError("Number of classes not supported for mobilenet");
}
- return 1;
+ return true;
}
void MobilenetDetection::preprocess(cv::Mat &frame, const int bi){
diff --git a/src/Yolo.cpp b/src/Yolo.cpp
index e6fb8ab..b68e1f6 100644
--- a/src/Yolo.cpp
+++ b/src/Yolo.cpp
@@ -278,6 +278,7 @@ void Yolo::mergeDetections(Yolo::detection *dets, int ndets, int classes, double
}
total = k+1;
+ float thresh = 0.45f;
for(k = 0; k < classes; ++k){
for(i = 0; i < total; ++i){
dets[i].sort_class = k;
@@ -288,9 +289,9 @@ void Yolo::mergeDetections(Yolo::detection *dets, int ndets, int classes, double
box a = dets[i].bbox;
for(j = i+1; j < total; ++j){
box b = dets[j].bbox;
- if (nsm_kind == GREEDY_NMS && yolo_box_iou(a, b) > nms_thresh)
+ if (nsm_kind == GREEDY_NMS && yolo_box_iou(a, b) > thresh)
dets[j].prob[k] = 0;
- else if (nsm_kind == DIOU_NMS && yolo_box_diou(a, b, nms_thresh) > nms_thresh)
+ else if (nsm_kind == DIOU_NMS && yolo_box_diou(a, b, nms_thresh) > thresh)
dets[j].prob[k] = 0;
}
}
diff --git a/tests/darknet/cfg/yolo4-csp_crowd.cfg b/tests/darknet/cfg/yolo4-csp_crowd.cfg
new file mode 100644
index 0000000..4c50f4d
--- /dev/null
+++ b/tests/darknet/cfg/yolo4-csp_crowd.cfg
@@ -0,0 +1,1279 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=64
+subdivisions=16
+width=512
+height=512
+channels=3
+momentum=0.949
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 8000
+policy=steps
+steps=6400,7200
+scales=.1,.1
+
+mosaic=1
+
+letter_box=1
+
+ema_alpha=0.9998
+
+#optimized_memory=1
+
+#23:104x104 54:52x52 85:26x26 104:13x13 for 416
+
+
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=mish
+
+#[convolutional]
+#batch_normalize=1
+#filters=64
+#size=1
+#stride=1
+#pad=1
+#activation=mish
+
+#[route]
+#layers = -2
+
+#[convolutional]
+#batch_normalize=1
+#filters=64
+#size=1
+#stride=1
+#pad=1
+#activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+#[convolutional]
+#batch_normalize=1
+#filters=64
+#size=1
+#stride=1
+#pad=1
+#activation=mish
+
+#[route]
+#layers = -1,-7
+
+#[convolutional]
+#batch_normalize=1
+#filters=64
+#size=1
+#stride=1
+#pad=1
+#activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-10
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-28
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-28
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-16
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=1
+stride=1
+pad=1
+activation=mish
+
+##########################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+### SPP ###
+[maxpool]
+stride=1
+size=5
+
+[route]
+layers=-2
+
+[maxpool]
+stride=1
+size=9
+
+[route]
+layers=-4
+
+[maxpool]
+stride=1
+size=13
+
+[route]
+layers=-1,-3,-5,-6
+### End SPP ###
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=mish
+
+[route]
+layers = -1, -13
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 79
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=mish
+
+[route]
+layers = -1, -6
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 48
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=128
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=128
+activation=mish
+
+[route]
+layers = -1, -6
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=mish
+
+##########################
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=21
+activation=logistic
+
+
+[yolo]
+mask = 0,1,2
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=2
+num=9
+jitter=.1
+scale_x_y = 2.0
+objectness_smooth=0
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=4.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+max_delta=5
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=256
+activation=mish
+
+[route]
+layers = -1, -20
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=mish
+
+[route]
+layers = -1,-6
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=21
+activation=logistic
+
+
+[yolo]
+mask = 3,4,5
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=2
+num=9
+jitter=.1
+scale_x_y = 2.0
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=1.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+max_delta=5
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=512
+activation=mish
+
+[route]
+layers = -1, -49
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=mish
+
+[route]
+layers = -1,-6
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=21
+activation=logistic
+
+
+[yolo]
+mask = 6,7,8
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=2
+num=9
+jitter=.1
+scale_x_y = 2.0
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=0.4
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+max_delta=2
diff --git a/tests/darknet/names/crowdhuman.names b/tests/darknet/names/crowdhuman.names
new file mode 100644
index 0000000..5ba1275
--- /dev/null
+++ b/tests/darknet/names/crowdhuman.names
@@ -0,0 +1,2 @@
+person
+head
\ No newline at end of file
diff --git a/tests/darknet/yolo4-csp_crowd.cpp b/tests/darknet/yolo4-csp_crowd.cpp
new file mode 100644
index 0000000..b8f0e6b
--- /dev/null
+++ b/tests/darknet/yolo4-csp_crowd.cpp
@@ -0,0 +1,34 @@
+#include
+#include
+#include "tkdnn.h"
+#include "test.h"
+#include "DarknetParser.h"
+
+int main() {
+ std::string bin_path = "yolo4-csp_crowd";
+ std::vector input_bins = {
+ bin_path + "/layers/input.bin"
+ };
+ std::vector output_bins = {
+ bin_path + "/debug/layer144_out.bin",
+ bin_path + "/debug/layer159_out.bin",
+ bin_path + "/debug/layer174_out.bin"
+ };
+ std::string wgs_path = bin_path + "/layers";
+ std::string cfg_path = std::string(TKDNN_PATH) + "/tests/darknet/cfg/yolo4-csp_crowd.cfg";
+ std::string name_path = std::string(TKDNN_PATH) + "/tests/darknet/names/crowdhuman.names";
+ downloadWeightsifDoNotExist(input_bins[0], bin_path, "https://cloud.hipert.unimore.it/s/RKWfWNmWXfJigsK/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;
+}
\ No newline at end of file
diff --git a/tests/darknet/yolo4_berkeley_f1.cpp b/tests/darknet/yolo4_berkeley_f1.cpp
index f6f4e62..7d830c3 100644
--- a/tests/darknet/yolo4_berkeley_f1.cpp
+++ b/tests/darknet/yolo4_berkeley_f1.cpp
@@ -17,7 +17,7 @@ int main() {
std::string wgs_path = bin_path + "/layers";
std::string cfg_path = std::string(TKDNN_PATH) + "/tests/darknet/cfg/yolo4_berkeley.cfg";
std::string name_path = std::string(TKDNN_PATH) + "/tests/darknet/names/berkeley.names";
- downloadWeightsifDoNotExist(input_bins[0], bin_path, "https://cloud.hipert.unimore.it/s/M7WJdGoGDaDACnN/download");
+ downloadWeightsifDoNotExist(input_bins[0], bin_path, "https://cloud.hipert.unimore.it/s/q9dwoqQ5YQqEi7s/download");
// parse darknet network
tk::dnn::Network *net = tk::dnn::darknetParser(cfg_path, wgs_path, name_path);
diff --git a/tests/shelfnet/shelfnet_coco.cpp b/tests/shelfnet/shelfnet_coco.cpp
new file mode 100644
index 0000000..276a09d
--- /dev/null
+++ b/tests/shelfnet/shelfnet_coco.cpp
@@ -0,0 +1,295 @@
+#include
+#include
+#include
+
+#include "tkdnn.h"
+#include "NetworkViz.h"
+
+
+const char *input_bin = "shelfnet_coco/debug/input.bin";
+
+const char *backbone[] = {
+ "shelfnet_coco/layers/backbone-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer1-0-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer1-0-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer1-1-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer1-1-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer2-0-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer2-0-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer2-0-downsample-0.bin",
+ "shelfnet_coco/layers/backbone-layer2-1-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer2-1-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer3-0-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer3-0-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer3-0-downsample-0.bin",
+ "shelfnet_coco/layers/backbone-layer3-1-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer3-1-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer4-0-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer4-0-conv2.bin",
+ "shelfnet_coco/layers/backbone-layer4-0-downsample-0.bin",
+ "shelfnet_coco/layers/backbone-layer4-1-conv1.bin",
+ "shelfnet_coco/layers/backbone-layer4-1-conv2.bin"};
+
+const char *conv_out[] = {
+ "shelfnet_coco/layers/conv_out-conv-conv.bin",
+ "shelfnet_coco/layers/conv_out-conv_out.bin",
+ "shelfnet_coco/layers/conv_out16-conv-conv.bin",
+ "shelfnet_coco/layers/conv_out16-conv_out.bin",
+ "shelfnet_coco/layers/conv_out32-conv-conv.bin",
+ "shelfnet_coco/layers/conv_out32-conv_out.bin"
+ };
+
+const char *decoder[] = {
+ "shelfnet_coco/layers/decoder-bottom-conv1.bin",
+ "shelfnet_coco/layers/decoder-bottom-conv12.bin",
+ "shelfnet_coco/layers/decoder-up_conv_list-0-conv-conv.bin",
+ "shelfnet_coco/layers/decoder-up_conv_list-0-conv_atten.bin",
+ "shelfnet_coco/layers/decoder-up_dense_list-0-conv.bin",
+ "shelfnet_coco/layers/decoder-up_conv_list-1-conv-conv.bin",
+ "shelfnet_coco/layers/decoder-up_conv_list-1-conv_atten.bin",
+ "shelfnet_coco/layers/decoder-up_dense_list-1-conv.bin"
+ };
+
+
+const char *ladder[] = {
+ "shelfnet_coco/layers/ladder-inconv-conv1.bin",
+ "shelfnet_coco/layers/ladder-inconv-conv12.bin",
+ "shelfnet_coco/layers/ladder-down_module_list-0-conv1.bin",
+ "shelfnet_coco/layers/ladder-down_module_list-0-conv12.bin",
+ "shelfnet_coco/layers/ladder-down_conv_list-0.bin",
+
+ "shelfnet_coco/layers/ladder-down_module_list-1-conv1.bin",
+ "shelfnet_coco/layers/ladder-down_module_list-1-conv12.bin",
+ "shelfnet_coco/layers/ladder-down_conv_list-1.bin",
+
+ "shelfnet_coco/layers/ladder-bottom-conv1.bin",
+ "shelfnet_coco/layers/ladder-bottom-conv12.bin",
+
+
+
+ "shelfnet_coco/layers/ladder-up_conv_list-0-conv-conv.bin",
+ "shelfnet_coco/layers/ladder-up_conv_list-0-conv_atten.bin",
+ "shelfnet_coco/layers/ladder-up_dense_list-0-conv.bin",
+
+
+ "shelfnet_coco/layers/ladder-up_conv_list-1-conv-conv.bin",
+ "shelfnet_coco/layers/ladder-up_conv_list-1-conv_atten.bin",
+ "shelfnet_coco/layers/ladder-up_dense_list-1-conv.bin"};
+
+const char *trans[] = {
+ "shelfnet_coco/layers/trans1-conv.bin",
+ "shelfnet_coco/layers/trans2-conv.bin",
+ "shelfnet_coco/layers/trans3-conv.bin"};
+int main()
+{
+
+ downloadWeightsifDoNotExist(input_bin, "shelfnet_coco", "https://cloud.hipert.unimore.it/s/KfQ9fGJQsgzNbiW/download");
+
+ int classes = 183;
+
+ // Network layout
+ tk::dnn::dataDim_t dim(1, 3, 1024, 1024, 1);
+ tk::dnn::Network net(dim);
+
+ int bi = 0, di = 0, li = 0, ci = 0;
+ new tk::dnn::Conv2d(&net, 64, 7, 7, 2, 2, 3, 3, backbone[bi++], true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ tk::dnn::Layer* last = new tk::dnn::Pooling (&net, 3, 3, 2, 2, 1, 1, tk::dnn::POOLING_MAX);
+
+
+
+ for(int i=0; i<2; ++i){
+ new tk::dnn::Conv2d (&net, 64, 3, 3, 1, 1, 1, 1, backbone[bi++], true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, 64, 3, 3, 1, 1, 1, 1, backbone[bi++], true);
+ new tk::dnn::Shortcut(&net, last);
+ last = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_RELU);
+ }
+
+ std::vector features;
+ for(int i=0;i<3;++i){
+ int out_channel = pow(2,7+i);
+ std::cout< up_out;
+ //bottom
+ new tk::dnn::Conv2d (&net, 256, 3, 3, 1, 1, 1, 1, decoder[di++], true, false, 1, true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, 256, 3, 3, 1, 1, 1, 1, decoder[di++], true, false, 1, true);
+ new tk::dnn::Shortcut(&net, last);
+ last = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_RELU);
+ up_out.push_back(last);
+
+ for(int i=0; i<2; ++i){
+ int out_channel = pow(2,7-i);
+ //up-conv
+ std::cout<output_dim.w, last->output_dim.h, last->output_dim.w, last->output_dim.h, 0, 0, tk::dnn::POOLING_AVERAGE);
+ new tk::dnn::Conv2d (&net, out_channel, 1, 1, 1, 1, 0, 0, decoder[di++], true);
+
+ tk::dnn::Layer* act = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_SIGMOID);
+ new tk::dnn::Route(&net, &last, 1);
+ new tk::dnn::Shortcut(&net, act, true);
+
+ //interpolate
+ new tk::dnn::Resize(&net, 1,2,2);
+ new tk::dnn::Shortcut(&net, features[1-i]);
+
+ //up-dense
+ new tk::dnn::Conv2d (&net, out_channel, 3, 3, 1, 1, 1, 1, decoder[di++], true);
+ last = new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ up_out.push_back(last);
+ }
+
+ //LADDER
+
+ std::vector down_out;
+ new tk::dnn::Conv2d (&net, 64, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, 64, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Shortcut(&net, last);
+ new tk::dnn::Activation (&net, CUDNN_ACTIVATION_RELU);
+
+ for(int i=0; i<2;++i){
+ int out_channel = pow(2,6+i);
+ tk::dnn::Layer* l_last = new tk::dnn::Shortcut(&net, up_out[2-i]);
+
+ new tk::dnn::Conv2d (&net, out_channel, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, out_channel, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Shortcut(&net, l_last);
+ l_last = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_RELU);
+ down_out.push_back(l_last);
+
+ new tk::dnn::Conv2d (&net, out_channel*2, 3, 3, 2, 2, 1, 1, ladder[li++], false);
+ last = new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.0f); //should be ReLU
+ }
+
+ new tk::dnn::Conv2d (&net, 256, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, 256, 3, 3, 1, 1, 1, 1, ladder[li++], true, false, 1, true);
+ new tk::dnn::Shortcut(&net, last);
+ last = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_RELU);
+ up_out.clear();
+ up_out.push_back(last);
+
+ for(int i=0; i<2; ++i){
+ int out_channel = pow(2,7-i);
+ //up-conv
+ new tk::dnn::Conv2d (&net, out_channel, 3, 3, 1, 1, 1, 1, ladder[li++], true);
+ last = new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+
+ new tk::dnn::Pooling(&net, last->output_dim.w, last->output_dim.h, last->output_dim.w, last->output_dim.h, 0, 0, tk::dnn::POOLING_AVERAGE);
+ new tk::dnn::Conv2d (&net, out_channel, 1, 1, 1, 1, 0, 0, ladder[li++], true);
+
+ tk::dnn::Layer* act = new tk::dnn::Activation (&net, CUDNN_ACTIVATION_SIGMOID);
+ new tk::dnn::Route(&net, &last, 1);
+ new tk::dnn::Shortcut(&net, act, true);
+
+ //interpolate
+ new tk::dnn::Resize(&net, 1,2,2);
+ new tk::dnn::Shortcut(&net, down_out[1-i]);
+
+ // //up-dense
+ new tk::dnn::Conv2d (&net, out_channel, 3, 3, 1, 1, 1, 1, ladder[li++], true);
+ last = new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ up_out.push_back(last);
+ }
+
+
+ // for(int i=2;i>=0;--i){
+ // new tk::dnn::Route(&net, &up_out[i], 1);
+ new tk::dnn::Conv2d (&net, 64, 3, 3, 1, 1, 1, 1, conv_out[ci++], true);
+ new tk::dnn::Activation (&net, tk::dnn::ACTIVATION_LEAKY, 0.0f, 0.01);
+ new tk::dnn::Conv2d (&net, classes, 3, 3, 1, 1, 1, 1, conv_out[ci++], false);
+ /*up_out[i] =*/ new tk::dnn::Resize(&net, classes, net.input_dim.h, net.input_dim.w, true, tk::dnn::ResizeMode_t::LINEAR);
+ // // }
+
+ new tk::dnn::Softmax(&net);
+
+ const char *output_bin = "shelfnet_coco/debug/softmax.bin";
+
+ // Load input
+ dnnType *data;
+ dnnType *input_h;
+ readBinaryFile(input_bin, dim.tot(), &input_h, &data);
+ std::cout<<"Input:"<
#include
-#include "tkdnn.h"
+#include "tkDNN/tkdnn.h"
#include /* srand, rand */
@@ -66,11 +66,11 @@ int main(int argc, char *argv[]) {
}
}
- double min = *std::min_element(stats.begin(), stats.end())/BATCH_SIZE;
- double max = *std::max_element(stats.begin(), stats.end())/BATCH_SIZE;
+ double min = *std::min_element(stats.begin(), stats.end()); ///BATCH_SIZE;
+ double max = *std::max_element(stats.begin(), stats.end()); ///BATCH_SIZE;
double mean =0;
for(int i=0; i