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

Merge with master

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2020-09-14 17:30:02 +02:00
parent 594947f301 fa2b3d26cb
commit 04b4a69107
32 changed files with 237 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+41 -15
View File
@@ -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.
@@ -14,8 +14,8 @@ M. Verucchi, G. Brilli, D. Sapienza, M. Verasani, M. Arena, F. Gatti, A. Capoton
"A Systematic Assessment of Embedded Neural Networks for Object Detection", in IEEE International Conference on Emerging Technologies and Factory Automation (2020)
```
## Results
Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimesion as the input size, on
## FPS Results
Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimension as the input size, on
* RTX 2080Ti (CUDA 10.2, TensorRT 7.0.0, Cudnn 7.6.5);
* Xavier AGX, Jetpack 4.3 (CUDA 10.0, CUDNN 7.6.3, tensorrt 6.0.1 );
* Tx2, Jetpack 4.2 (CUDA 10.0, CUDNN 7.3.1, tensorrt 5.0.6 );
@@ -40,6 +40,20 @@ Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimesio
| Nano | yolo4 512 | 2,32 | 2,34 | 3,02 | 3,04 | - | - |
| Nano | yolo4 608 | 1,40 | 1,41 | 1,92 | 1,93 | - | - |
## MAP Results
Results for COCO val 2017 (5k images), on RTX 2080Ti, with conf threshold=0.001
| | CodaLab | CodaLab | CodaLab | CodaLab | tkDNN map | tkDNN map |
| -------------------- | :-----------: | :-------: | :-----------: | :---------: | :-----------: | :-------: |
| | **tkDNN** | **tkDNN** | **darknet** | **darknet** | **tkDNN** | **tkDNN** |
| | MAP(0.5:0.95) | AP50 | MAP(0.5:0.95) | AP50 | MAP(0.5:0.95) | AP50 |
| Yolov3 (416x416) | 0.381 | 0.675 | 0.380 | 0.675 | 0.372 | 0.663 |
| yolov4 (416x416) | 0.468 | 0.705 | 0.471 | 0.710 | 0.459 | 0.695 |
| yolov3tiny (416x416) | 0.096 | 0.202 | 0.096 | 0.201 | 0.093 | 0.198 |
| yolov4tiny (416x416) | 0.202 | 0.400 | 0.201 | 0.400 | 0.197 | 0.395 |
| Cnet-dla34 (512x512) | 0.366 | 0.543 | \- | \- | 0.361 | 0.535 |
| mv2SSD (512x512) | 0.226 | 0.381 | \- | \- | 0.223 | 0.378 |
## Index
- [tkDNN](#tkdnn)
- [Index](#index)
@@ -155,7 +169,7 @@ tkDNN implement and easy parser for darknet cfg files, a network can be converte
tk::dnn::Network *net = tk::dnn::darknetParser("yolov4.cfg", "yolov4/layers", "coco.names");
net->print();
```
All models from darknet are now parsed directly from cfg, you still need to export the weights with the descripted tools in the previus section.
All models from darknet are now parsed directly from cfg, you still need to export the weights with the described tools in the previous section.
<details>
<summary>Supported layers</summary>
convolutional
@@ -175,15 +189,25 @@ 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 successfully created your rt file, run the demo:
```
./demo yolo4_fp32.rt ../demo/yolo_test.mp4 y
```
In general the demo program takes 7 parameters:
```
./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <n-batches> <show-flag>
```
@@ -194,9 +218,11 @@ where
* ```<number-of-classes>```is the number of classes the network is trained on
* ```<n-batches>``` number of batches to use in inference (N.B. you should first export TKDNN_BATCHSIZE to the required n_batches and create again the rt file for the network).
* ```<show-flag>``` if set to 0 the demo will not show the visualization but save the video into result.mp4 (if n-batches ==1)
* ```<conf-thresh>``` confidence threshold for the detector. Only bounding boxes with threshold greater than conf-thresh will be displayed.
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
@@ -221,7 +247,7 @@ You should provide image_list.txt and label_list.txt, using training images. How
```
bash scripts/download_validation.sh COCO
```
to automatically download COCO2017 validation (inside demo folder) and create those needed file. Use BDD insted of COCO to download BDD validation.
to automatically download COCO2017 validation (inside demo folder) and create those needed file. Use BDD instead of COCO to download BDD validation.
Then a complete example using yolo3 and COCO dataset would be:
```
@@ -243,8 +269,8 @@ N.B.
export TKDNN_BATCHSIZE=2
# build tensorRT files
```
This will create a TensorRT file with the desidered **max** batch size.
The test will still run with a batch of 1, but the created tensorRT can manage the desidered batch size.
This will create a TensorRT file with the desired **max** batch size.
The test will still run with a batch of 1, but the created tensorRT can manage the desired batch size.
### Test batch Inference
This will test the network with random input and check if the output of each batch is the same.
@@ -290,7 +316,7 @@ cd build
./map_demo dla34_cnet_FP32.rt c ../demo/COCO_val2017/all_labels.txt ../demo/config.yaml
```
This demo also creates a json file named ```net_name_COCO_res.json``` containing all the detections computed. The detections are in COCO format, the correct format to subit the results to [CodaLab COCO detection challenge](https://competitions.codalab.org/competitions/20794#participate).
This demo also creates a json file named ```net_name_COCO_res.json``` containing all the detections computed. The detections are in COCO format, the correct format to submit the results to [CodaLab COCO detection challenge](https://competitions.codalab.org/competitions/20794#participate).
## Existing tests and supported networks
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
+4 -2
View File
@@ -40,6 +40,9 @@ int main(int argc, char *argv[]) {
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");
@@ -69,8 +72,7 @@ int main(int argc, char *argv[]) {
FatalError("Network type not allowed (3rd parameter)\n");
}
float conf_thresh = 0.3;
detNN->init(net, conf_thresh, n_classes, n_batch);
detNN->init(net, n_classes, n_batch, conf_thresh);
gRun = true;
demo/demo/map.cpp
+1 -1
View File
@@ -113,7 +113,7 @@ int main(int argc, char *argv[])
default:
FatalError("Network type not allowed (3rd parameter)\n");
}
detNN->init(net, confidence_thresh, n_classes, n_batches);
detNN->init(net, n_classes, 1, conf_thresh);
//read images
std::ifstream all_labels(labels_path);
docker/Dockerfile
+7
View File
@@ -0,0 +1,7 @@
FROM ceccocats/tkdnn:latest
LABEL maintainer "Francesco Gatti"
RUN cd && git clone https://github.com/ceccocats/tkDNN.git && cd tkDNN && mkdir build && cd build \
&& cmake .. && make -j12
docker/Dockerfile.base
+57
View File
@@ -0,0 +1,57 @@
FROM nvidia/cuda:10.2-cudnn7-devel-ubuntu18.04
LABEL maintainer "Francesco Gatti"
ADD nv-tensorrt-repo-ubuntu1804-cuda10.2-trt7.0.0.11-ga-20191216_1-1_amd64.deb /tmp/trt.deb
RUN apt-get update && dpkg -i /tmp/trt.deb && rm /tmp/trt.deb && apt-get update
RUN apt install -y libnvinfer7=7.0.0-1+cuda10.2 libnvinfer-dev=7.0.0-1+cuda10.2
RUN DEBIAN_FRONTEND=noninteractive apt install -y git wget libeigen3-dev libyaml-cpp-dev
RUN cd /tmp && \
wget https://github.com/Kitware/CMake/releases/download/v3.17.3/cmake-3.17.3-Linux-x86_64.sh && \
chmod +x cmake-3.17.3-Linux-x86_64.sh && \
./cmake-3.17.3-Linux-x86_64.sh --prefix=/usr/local --exclude-subdir --skip-license && \
rm ./cmake-3.17.3-Linux-x86_64.sh
RUN echo "INSTALL OPENCV"
RUN apt-get install -y build-essential \
unzip \
pkg-config \
libjpeg-dev \
libpng-dev \
libtiff-dev \
libavcodec-dev \
libavformat-dev \
libswscale-dev \
libv4l-dev \
libxvidcore-dev \
libx264-dev \
libgtk-3-dev \
libatlas-base-dev \
gfortran \
libgstreamer1.0-dev \
libgstreamer-plugins-base1.0-dev \
libdc1394-22-dev \
libavresample-dev
RUN cd && wget https://github.com/opencv/opencv/archive/4.3.0.tar.gz && tar -xf 4.3.0.tar.gz && rm *.tar.gz
RUN cd && wget https://github.com/opencv/opencv_contrib/archive/4.3.0.tar.gz && tar -xf 4.3.0.tar.gz && rm *.tar.gz
RUN cd && \
cd opencv-4.3.0 && mkdir build && cd build && \
cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D INSTALL_PYTHON_EXAMPLES=OFF \
-D INSTALL_C_EXAMPLES=OFF \
-D OPENCV_EXTRA_MODULES_PATH='~/opencv_contrib-4.3.0/modules' \
-D BUILD_EXAMPLES=OFF \
-D WITH_CUDA=ON \
-D CUDA_ARCH_BIN=7.2 \
-D CUDA_ARCH_PTX="" \
-D ENABLE_FAST_MATH=ON \
-D CUDA_FAST_MATH=ON \
-D WITH_CUBLAS=ON \
-D WITH_LIBV4L=ON \
-D WITH_GSTREAMER=ON \
-D WITH_GSTREAMER_0_10=OFF \
-D WITH_TBB=ON \
../ && make -j12 && make install
RUN apt clean
docker/README.md
+21
View File
@@ -0,0 +1,21 @@
# Use the prebuilt image
```
# build image
docker build -t tkdnn:build -f Dockerfile .
```
# Build Base Docker image
```
# make nvidia docker working
# follow this guide: https://github.com/NVIDIA/nvidia-docker
# dowload tensorrt
# from: https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/7.0/7.0.0.11/local_repo/nv-tensorrt-repo-ubuntu1804-cuda10.2-trt7.0.0.11-ga-20191216_1-1_amd64.deb
# build image
docker build -t ceccocats/tkdnn:latest -f Dockerfile.base .
# run image
docker run -ti --gpus all --rm ceccocats/tkdnn:latest bash
```
include/tkDNN/CenternetDetection.h
+1 -1
View File
@@ -73,7 +73,7 @@ public:
CenternetDetection() {};
~CenternetDetection() {};
bool init(const std::string& tensor_path, const float conf_threshold, const int n_classes=80, const int n_batches=1);
bool init(const std::string& tensor_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3);
void preprocess(cv::Mat &frame, const int bi=0);
void postprocess(const int bi=0,const bool mAP=false);
};
include/tkDNN/DetectionNN.h
+5 -5
View File
@@ -76,15 +76,15 @@ class DetectionNN {
~DetectionNN(){};
/**
* Method used to inialize the class, allocate memory and compute
* Method used to initialize the class, allocate memory and compute
* needed data.
*
* @param tensor_path path to the rt file og the NN.
* @param tensor_path path to the rt file of the NN.
* @param n_classes number of classes for the given dataset.
* @param n_batches maximum number of batches to use in inference
* @return true if everything is correct, false otherwise.
*/
virtual bool init(const std::string& tensor_path, const float conf_threshold, const int n_classes=80, const int n_batches=1) = 0;
virtual bool init(const std::string& tensor_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3) = 0;
/**
* This method performs the whole detection of the NN.
@@ -141,9 +141,9 @@ class DetectionNN {
}
/**
* Method to draw boundixg boxes and labels on a frame.
* Method to draw bounding boxes and labels on a frame.
*
* @param frames orginal frame to draw bounding box on.
* @param frames original frame to draw bounding box on.
*/
void draw(std::vector<cv::Mat>& frames) {
tk::dnn::box b;
include/tkDNN/ImuOdom.h
+2 -2
View File
@@ -44,7 +44,7 @@ class ImuOdom {
virtual ~ImuOdom() {}
/**
* Method used for inizialize the class
* Method used for initialize the class
*
* @return Success of the initialization
*/
@@ -141,7 +141,7 @@ class ImuOdom {
//odomPOS = odomPOS + deltaP.cast<double>(); // V2
odomROT = odomROT * q.normalized().toRotationMatrix();
// compute euler
// compute Euler
auto newEULER = odomROT.eulerAngles(0, 1, 2);
for(int i=0; i<3; i++) {
while( fabs(newEULER(i) - odomEULER(i)) > M_PI_2 ) {
include/tkDNN/Layer.h
+12 -12
View File
@@ -171,7 +171,7 @@ public:
/**
Input layer (it doesnt need weigths)
Input layer (it doesn't need weights)
*/
class Input : public Layer {
@@ -207,7 +207,7 @@ public:
/**
Avaible activation functions
Available activation functions
*/
typedef enum {
ACTIVATION_ELU = 100,
@@ -216,7 +216,7 @@ typedef enum {
} tkdnnActivationMode_t;
/**
Activation layer (it doesnt need weigths)
Activation layer (it doesn't need weights)
*/
class Activation : public Layer {
@@ -273,8 +273,8 @@ public:
protected:
cudnnFilterDescriptor_t filterDesc;
cudnnConvolutionDescriptor_t convDesc;
cudnnConvolutionFwdAlgo_t algo;
cudnnConvolutionBwdDataAlgo_t bwAlgo;
cudnnConvolutionFwdAlgoPerf_t algo;
cudnnConvolutionBwdDataAlgoPerf_t bwAlgo;
cudnnTensorDescriptor_t biasTensorDesc;
void initCUDNN(bool back = false);
@@ -318,9 +318,9 @@ public:
virtual dnnType* infer(dataDim_t &dim, dnnType* srcData);
const bool bidirectional = true; /**> is the net bidir */
bool returnSeq = false; /**> if false return only the result of last timestep */
bool returnSeq = false; /**> if false return only the result of last timestamp */
int stateSize = 0; /**> number of hidden states */
int seqLen = 0; /**> number of timesteps */
int seqLen = 0; /**> number of timestamp */
int numLayers = 1; /**> number of internal layers */
protected:
@@ -367,7 +367,7 @@ public:
/**
Deformable Convolutionl 2d layer
Deformable Convolutional 2d layer
*/
class DeformConv2d : public LayerWgs {
@@ -449,7 +449,7 @@ protected:
/**
Avaible pooling functions (padding on tkDNN is not supported)
Available pooling functions (padding on tkDNN is not supported)
*/
typedef enum {
POOLING_MAX = 0,
@@ -460,7 +460,7 @@ typedef enum {
/**
Pooling layer
currenty supported only 2d pooing (also on 3d input)
currently supported only 2d pooing (also on 3d input)
*/
class Pooling : public Layer {
@@ -526,7 +526,7 @@ public:
/**
Reorg layer
Mantain same dimension but change C*H*W distribution
Maintains same dimension but change C*H*W distribution
*/
class Reorg : public Layer {
@@ -559,7 +559,7 @@ public:
/**
Upsample layer
Mantain same dimension but change C*H*W distribution
Maintains same dimension but change C*H*W distribution
*/
class Upsample : public Layer {
include/tkDNN/MobilenetDetection.h
+1 -1
View File
@@ -65,7 +65,7 @@ public:
MobilenetDetection() {};
~MobilenetDetection() {};
bool init(const std::string& tensor_path, const float conf_threshold, const int n_classes, const int n_batches=1);
bool init(const std::string& tensor_path, const int n_classes, const int n_batches=1, const float conf_thresh=0.3);
void preprocess(cv::Mat &frame, const int bi=0);
void postprocess(const int bi=0,const bool mAP=false);
};
include/tkDNN/Network.h
+4 -4
View File
@@ -7,12 +7,12 @@
namespace tk { namespace dnn {
/**
Data rapresentation beetween layers
Data representation between layers
n = batch size
c = channels
h = heigth (lines)
h = height (lines)
w = width (rows)
l = lenght (3rd dimension)
l = length (3rd dimension)
*/
struct dataDim_t {
@@ -43,7 +43,7 @@ public:
void releaseLayers();
/**
Do inferece for every added layer
Do inference for every added layer
*/
dnnType* infer(dataDim_t &dim, dnnType* data);
include/tkDNN/NetworkRT.h
+1 -1
View File
@@ -91,7 +91,7 @@ public:
}
/**
Do inferece
Do inference
*/
dnnType* infer(dataDim_t &dim, dnnType* data);
void enqueue(int batchSize = 1);
include/tkDNN/Yolo3Detection.h
+1 -1
View File
@@ -24,7 +24,7 @@ public:
Yolo3Detection() {};
~Yolo3Detection() {};
bool init(const std::string& tensor_path, const float conf_threshold, const int n_classes=80, const int n_batches=1);
bool init(const std::string& tensor_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3);
void preprocess(cv::Mat &frame, const int bi=0);
void postprocess(const int bi=0,const bool mAP=false);
};
include/tkDNN/evaluation.h
+4 -4
View File
@@ -75,12 +75,12 @@ double computeMap( std::vector<Frame> &images,const int classes,
* all the recall levels are evaluated, otherwise only
* map_point recall levels are used. For COCO evaluation
* 101 points are used.
* @param map_step step used to increment IoU theshold
* @param map_step step used to increment IoU threshold
* @param map_levels number of IoU step to perform
* @param verbose is set to true, prints on screen additional info
* @param write_on_file if set to true, the results produced by this function
* are written on file
* @param net name of the considerd neural network
* @param net name of the considered neural network
*
* @return mAP IoU_tresh:IoU_tresh+map_step*map_levels (e.g. mAP 0.5:0.95 when
* map_step=0.05 and map_levels=10)
@@ -91,7 +91,7 @@ double computeMapNIoULevels(std::vector<Frame> &images,const int classes,
const int map_levels=10, const bool verbose=false,
const bool write_on_file = false, std::string net = "");
/**
* This method computes the numper of True Positive (TP), False Positive (FP),
* This method computes the number of True Positive (TP), False Positive (FP),
* False Negative (FN), precision, recall and f1-score.
* Those values are computer over all the detections, over all the classes.
*
@@ -103,7 +103,7 @@ double computeMapNIoULevels(std::vector<Frame> &images,const int classes,
* @param verbose is set to true, prints on screen additional info
* @param write_on_file if set to true, the results produced by this function
* are written on file
* @param net name of the considerd neural network
* @param net name of the considered neural network
*/
void computeTPFPFN( std::vector<Frame> &images,const int classes,
const float IoU_thresh=0.5, const float conf_thresh=0.3,
include/tkDNN/pluginsRT/DeformableConvRT.h
+1 -1
View File
@@ -89,7 +89,7 @@ public:
for(int b=0; b<batchSize; b++) {
checkCuda(cudaMemcpy(offset, output_conv + b * 3 * chunk_dim, 2*chunk_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
checkCuda(cudaMemcpy(mask, output_conv + b * 3 * chunk_dim + 2*chunk_dim, chunk_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
// kernel sigmoide
// kernel sigmoid
activationSIGMOIDForward(mask, mask, chunk_dim);
// deformable convolution
dcnV2CudaForward(stat, handle,
include/tkDNN/test.h
+1 -1
View File
@@ -20,7 +20,7 @@ int testInference(std::vector<std::string> input_bins, std::vector<std::string>
}
if(output_bins.size() != outputs.size()) {
std::cout<<output_bins.size()<<" "<<outputs.size()<<"\n";
FatalError("outputs size missmatch");
FatalError("outputs size mismatch");
}
// Load input
src/CenternetDetection.cpp
+6 -6
View File
@@ -3,12 +3,12 @@
namespace tk { namespace dnn {
bool CenternetDetection::init(const std::string& tensor_path, const float conf_threshold, const int n_classes, const int n_batches){
bool CenternetDetection::init(const std::string& tensor_path, const int n_classes, const int n_batches, const float conf_thresh){
std::cout<<(tensor_path).c_str()<<"\n";
netRT = new tk::dnn::NetworkRT(NULL, (tensor_path).c_str() );
classes = n_classes;
nBatches = n_batches;
confThreshold = conf_threshold;
confThreshold = conf_thresh;
dim = netRT->input_dim;
@@ -372,10 +372,10 @@ void CenternetDetection::postprocess(const int bi, const bool mAP){
// std::cout<<"th: "<<scores[j]<<" - cl: "<<clses[j]<<" i: "<<i<<std::endl;
//add coco bbox
//det[0:4], i, det[4]
int x0 = target_coords[j*4];
int y0 = target_coords[j*4+1];
int x1 = target_coords[j*4+2];
int y1 = target_coords[j*4+3];
float x0 = target_coords[j*4];
float y0 = target_coords[j*4+1];
float x1 = target_coords[j*4+2];
float y1 = target_coords[j*4+3];
int obj_class = clses[j];
float prob = scores[j];
// std::cout<<"("<<x0<<", "<<y0<<"),("<<x1<<", "<<y1<<")"<<std::endl;
src/Conv2d.cpp
+18 -13
View File
@@ -62,25 +62,30 @@ void Conv2d::initCUDNN(bool back) {
// init workspace
workSpace = NULL;
ws_sizeInBytes = 0;
int algo_count = 0;
if(back) {
checkCUDNN( cudnnGetConvolutionBackwardDataAlgorithm(net->cudnnHandle,
filterDesc, dstTensor, convDesc, srcTensor,
CUDNN_CONVOLUTION_BWD_DATA_PREFER_FASTEST, 0, &bwAlgo) );
checkCUDNN( cudnnGetConvolutionBackwardDataAlgorithm_v7(net->cudnnHandle,
filterDesc, dstTensor, convDesc, srcTensor, 1, &algo_count, &bwAlgo) );
checkCUDNN(cudnnGetConvolutionBackwardDataWorkspaceSize(net->cudnnHandle,
filterDesc, dstTensor, convDesc, srcTensor,
bwAlgo, &ws_sizeInBytes));
filterDesc, dstTensor, convDesc, srcTensor,
bwAlgo.algo, &ws_sizeInBytes));
// invert tensors
srcTensorDesc = dstTensor;
dstTensorDesc = srcTensor;
} else {
checkCUDNN( cudnnGetConvolutionForwardAlgorithm(net->cudnnHandle,
srcTensor, filterDesc, convDesc, dstTensor,
CUDNN_CONVOLUTION_FWD_PREFER_FASTEST, 0, &algo) );
checkCUDNN(cudnnGetConvolutionForwardWorkspaceSize(net->cudnnHandle,
srcTensor, filterDesc, convDesc, dstTensor,
algo, &ws_sizeInBytes));
checkCUDNN( cudnnGetConvolutionForwardAlgorithm_v7(net->cudnnHandle,
srcTensor, filterDesc, convDesc, dstTensor,
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) {
@@ -91,12 +96,12 @@ void Conv2d::inferCUDNN(dnnType* srcData, bool back) {
checkCUDNN(cudnnConvolutionBackwardData(net->cudnnHandle,
&alpha, filterDesc, data_d,
srcTensorDesc, srcData,
convDesc, bwAlgo, workSpace, ws_sizeInBytes,
convDesc, bwAlgo.algo, workSpace, ws_sizeInBytes,
&beta, dstTensorDesc, dstData));
} else {
checkCUDNN(cudnnConvolutionForward(net->cudnnHandle,
&alpha, srcTensorDesc, srcData, filterDesc,
data_d, convDesc, algo, workSpace, ws_sizeInBytes,
data_d, convDesc, algo.algo, workSpace, ws_sizeInBytes,
&beta, dstTensorDesc, dstData));
}
src/DarknetParser.cpp
+1 -1
View File
@@ -201,7 +201,7 @@ namespace tk { namespace dnn {
tk::dnn::Network *net = nullptr;
// layers without activations to retrive correct id number
// layers without activations to retrieve correct id number
std::vector<tk::dnn::Layer*> netLayers;
std::ifstream if_cfg(cfg_file);
src/DeformConv2d.cpp
+1 -1
View File
@@ -95,7 +95,7 @@ dnnType* DeformConv2d::infer(dataDim_t &dim, dnnType* srcData) {
// split conv2d outputs into offset and mask
checkCuda(cudaMemcpy(offset, output_conv, 2*chunk_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
checkCuda(cudaMemcpy(mask, output_conv + 2*chunk_dim, chunk_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice));
// kernel sigmoide
// kernel sigmoid
activationSIGMOIDForward(mask, mask, chunk_dim);
// deformable convolution
src/Dense.cpp
+1 -1
View File
@@ -37,7 +37,7 @@ dnnType* Dense::infer(dataDim_t &dim, dnnType* srcData) {
// place bias into dstData
checkCuda( cudaMemcpy(dstData, bias_d, dim_y*sizeof(dnnType), cudaMemcpyDeviceToDevice) );
//do matrix moltiplication
//do matrix multiplication
checkERROR( cublasSgemv(net->cublasHandle, CUBLAS_OP_T,
dim_x, dim_y,
&alpha,
src/LSTM.cpp
+5 -5
View File
@@ -133,7 +133,7 @@ LSTM::LSTM( Network *net, int hiddensize, bool returnSeq, std::string fname_weig
output_dim = input_dim;
output_dim.c = stateSize*(bidirectional ? 2 : 1);
// if retunseq is disabled only the last timestep is returned
// if retunseq is disabled only the last timestamp is returned
if(!returnSeq) {
output_dim.h = 1;
output_dim.w = 1;
@@ -254,7 +254,7 @@ dnnType* LSTM::infer(dataDim_t &dim, dnnType* srcData) {
rnnDesc,
seqLen, // number of time steps (nT)
x_desc_vec_.data(), // input array of desc (nT*nC_in)
srcF, // input pointer
srcF, // input pointer
hx_desc_, // initial hidden state desc
hx_ptr, // initial hidden state pointer
cx_desc_, // initial cell state desc
@@ -281,7 +281,7 @@ dnnType* LSTM::infer(dataDim_t &dim, dnnType* srcData) {
rnnDesc,
seqLen, // number of time steps (nT)
x_desc_vec_.data(), // input array of desc (nT*nC_in)
srcB, // input pointer
srcB, // input pointer
hx_desc_, // initial hidden state desc
hx_ptr, // initial hidden state pointer
cx_desc_, // initial cell state desc
@@ -289,7 +289,7 @@ dnnType* LSTM::infer(dataDim_t &dim, dnnType* srcData) {
w_desc_, // weights desc
wb_ptr, // weights pointer
y_desc_vec_.data(), // output desc (nT*nC_out)
dstB_NR, // output pointer
dstB_NR, // output pointer
hy_desc_, // final hidden state desc
hy_ptr, // final hidden state pointer
cy_desc_, // final cell state desc
@@ -307,7 +307,7 @@ dnnType* LSTM::infer(dataDim_t &dim, dnnType* srcData) {
one_output_dim.c*sizeof(dnnType), cudaMemcpyDeviceToDevice));
}
// if retunseq is disabled only the last timestep is returned
// if retunseq is disabled only the last timestamp is returned
if(returnSeq) {
// forward transpose
matrixTranspose(net->cublasHandle, dstF, dstData,
src/LayerWgs.cpp
+1 -1
View File
@@ -105,7 +105,7 @@ LayerWgs::LayerWgs(Network *net, int inputs, int outputs,
float2half(tmp_d, variance16_d, b_size);
cudaMemcpy(variance16_h, variance16_d, b_size*sizeof(__half), cudaMemcpyDeviceToHost);
//conver scales
//convert scales
float2half(scales_d, scales16_d, b_size);
cudaMemcpy(scales16_h, scales16_d, b_size*sizeof(__half), cudaMemcpyDeviceToHost);
src/MobilenetDetection.cpp
+2 -2
View File
@@ -126,13 +126,13 @@ float MobilenetDetection::iou(const tk::dnn::box &a, const tk::dnn::box &b){
return iou;
}
bool MobilenetDetection::init(const std::string& tensor_path, const float conf_threshold, const int n_classes, const int n_batches){
bool MobilenetDetection::init(const std::string& tensor_path, const int n_classes, const int n_batches, const float conf_thresh){
std::cout<<(tensor_path).c_str()<<"\n";
netRT = new tk::dnn::NetworkRT(NULL, (tensor_path).c_str());
imageSize = netRT->input_dim.h;
classes = n_classes;
nBatches = n_batches;
confThreshold = conf_threshold;
confThreshold = conf_thresh;
SSDSpec specs[N_SSDSPEC];
src/MulAdd.cpp
+1 -1
View File
@@ -12,7 +12,7 @@ MulAdd::MulAdd(Network *net, dnnType mul, dnnType add) : Layer(net) {
int size = input_dim.tot();
// create a vector with all value setted to add
// create a vector with all value set to add
dnnType *add_vector_h = new dnnType[size];
for(int i=0; i<size; i++)
add_vector_h[i] = add;
src/NetworkRT.cpp
+1 -1
View File
@@ -163,7 +163,7 @@ NetworkRT::NetworkRT(Network *net, const char *name) {
// note that indices are guaranteed to be less than IEngine::getNbBindings()
buf_input_idx = engineRT->getBindingIndex("data");
buf_output_idx = engineRT->getBindingIndex("out");
std::cout<<"input idex = "<<buf_input_idx<<" -> output index = "<<buf_output_idx<<"\n";
std::cout<<"input index = "<<buf_input_idx<<" -> output index = "<<buf_output_idx<<"\n";
Dims iDim = engineRT->getBindingDimensions(buf_input_idx);
src/Region.cpp
+1 -1
View File
@@ -63,7 +63,7 @@ dnnType* Region::infer(dataDim_t &dim, dnnType* srcData) {
}
/* Intepret class */
/* Interpret class */
RegionInterpret::RegionInterpret(dataDim_t input_dim, dataDim_t output_dim,
int classes, int coords, int num, float thresh, std::string fname_weights) {
src/Shortcut.cpp
+1 -1
View File
@@ -13,7 +13,7 @@ Shortcut::Shortcut(Network *net, Layer *backLayer) : Layer(net) {
if( /*backLayer->output_dim.c != input_dim.c ||*/
backLayer->output_dim.w != input_dim.w ||
backLayer->output_dim.h != input_dim.h )
FatalError("Shortcut dim missmatch");
FatalError("Shortcut dim mismatch");
}
Shortcut::~Shortcut() {
src/Yolo3Detection.cpp
+30 -29
View File
@@ -3,14 +3,14 @@
namespace tk { namespace dnn {
bool Yolo3Detection::init(const std::string& tensor_path, const float conf_threshold, const int n_classes, const int n_batches) {
bool Yolo3Detection::init(const std::string& tensor_path, const int n_classes, const int n_batches, const float conf_thresh) {
//convert network to tensorRT
std::cout<<(tensor_path).c_str()<<"\n";
netRT = new tk::dnn::NetworkRT(NULL, (tensor_path).c_str() );
nBatches = n_batches;
confThreshold = conf_threshold;
confThreshold = conf_thresh;
tk::dnn::dataDim_t idim = netRT->input_dim;
idim.n = nBatches;
@@ -110,38 +110,39 @@ void Yolo3Detection::postprocess(const int bi, const bool mAP){
detected.clear();
for(int j=0; j<nDets; j++) {
tk::dnn::Yolo::box b = dets[j].bbox;
int x0 = (b.x-b.w/2.);
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;
float x0 = (b.x-b.w/2.);
float x1 = (b.x+b.w/2.);
float y0 = (b.y-b.h/2.);
float y1 = (b.y+b.h/2.);
// 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);
}
src/evaluation.cpp
+3 -3
View File
@@ -63,7 +63,7 @@ double computeMap( std::vector<Frame> &images,const int classes,
int gt_checked = 0;
// for each detection comput IoU with groundtruth and match detetcion and
// for each detection compute IoU with groundtruth and match detetcion and
// groundtruth with IoU greater than IoU_thresh
for(auto &img:images){
for(size_t i=0; i<img.det.size(); i++){
@@ -153,7 +153,7 @@ double computeMap( std::vector<Frame> &images,const int classes,
}
}
//compute average precision for each class. Two methods are avaible,
//compute average precision for each class. Two methods are available,
//based on map_points required
double mean_average_precision = 0;
double last_recall, last_precision, delta_recall;
@@ -287,7 +287,7 @@ void computeTPFPFN( std::vector<Frame> &images,const int classes,
}
}
//count all TP, FP, FN and compute precsion, recall and f1-score
//count all TP, FP, FN and compute precision, recall and f1-score
double avg_precision = 0, avg_recall = 0, f1_score = 0;
int TP = 0, FP = 0, FN = 0;
for(size_t i=0; i<classes; i++){