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
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++){