add cpp zero copy run interface
This commit is contained in:
parent
0a011e564a
commit
ed52619f4b
|
@ -41,6 +41,8 @@ public:
|
|||
|
||||
this->use_mkldnn = bool(stoi(config_map_["use_mkldnn"]));
|
||||
|
||||
this->use_zero_copy_run = bool(stoi(config_map_["use_zero_copy_run"]));
|
||||
|
||||
this->max_side_len = stoi(config_map_["max_side_len"]);
|
||||
|
||||
this->det_db_thresh = stod(config_map_["det_db_thresh"]);
|
||||
|
@ -68,6 +70,8 @@ public:
|
|||
|
||||
bool use_mkldnn = false;
|
||||
|
||||
bool use_zero_copy_run = false;
|
||||
|
||||
int max_side_len = 960;
|
||||
|
||||
double det_db_thresh = 0.3;
|
||||
|
|
|
@ -39,8 +39,8 @@ public:
|
|||
explicit DBDetector(const std::string &model_dir, const bool &use_gpu,
|
||||
const int &gpu_id, const int &gpu_mem,
|
||||
const int &cpu_math_library_num_threads,
|
||||
const bool &use_mkldnn, const int &max_side_len,
|
||||
const double &det_db_thresh,
|
||||
const bool &use_mkldnn, const bool &use_zero_copy_run,
|
||||
const int &max_side_len, const double &det_db_thresh,
|
||||
const double &det_db_box_thresh,
|
||||
const double &det_db_unclip_ratio,
|
||||
const bool &visualize) {
|
||||
|
@ -49,6 +49,7 @@ public:
|
|||
this->gpu_mem_ = gpu_mem;
|
||||
this->cpu_math_library_num_threads_ = cpu_math_library_num_threads;
|
||||
this->use_mkldnn_ = use_mkldnn;
|
||||
this->use_zero_copy_run_ = use_zero_copy_run;
|
||||
|
||||
this->max_side_len_ = max_side_len;
|
||||
|
||||
|
@ -75,6 +76,7 @@ private:
|
|||
int gpu_mem_ = 4000;
|
||||
int cpu_math_library_num_threads_ = 4;
|
||||
bool use_mkldnn_ = false;
|
||||
bool use_zero_copy_run_ = false;
|
||||
|
||||
int max_side_len_ = 960;
|
||||
|
||||
|
|
|
@ -38,12 +38,14 @@ public:
|
|||
explicit CRNNRecognizer(const std::string &model_dir, const bool &use_gpu,
|
||||
const int &gpu_id, const int &gpu_mem,
|
||||
const int &cpu_math_library_num_threads,
|
||||
const bool &use_mkldnn, const string &label_path) {
|
||||
const bool &use_mkldnn, const bool &use_zero_copy_run,
|
||||
const string &label_path) {
|
||||
this->use_gpu_ = use_gpu;
|
||||
this->gpu_id_ = gpu_id;
|
||||
this->gpu_mem_ = gpu_mem;
|
||||
this->cpu_math_library_num_threads_ = cpu_math_library_num_threads;
|
||||
this->use_mkldnn_ = use_mkldnn;
|
||||
this->use_zero_copy_run_ = use_zero_copy_run;
|
||||
|
||||
this->label_list_ = Utility::ReadDict(label_path);
|
||||
this->label_list_.push_back(" ");
|
||||
|
@ -64,6 +66,7 @@ private:
|
|||
int gpu_mem_ = 4000;
|
||||
int cpu_math_library_num_threads_ = 4;
|
||||
bool use_mkldnn_ = false;
|
||||
bool use_zero_copy_run_ = false;
|
||||
|
||||
std::vector<std::string> label_list_;
|
||||
|
||||
|
|
|
@ -48,14 +48,15 @@ int main(int argc, char **argv) {
|
|||
|
||||
cv::Mat srcimg = cv::imread(img_path, cv::IMREAD_COLOR);
|
||||
|
||||
DBDetector det(config.det_model_dir, config.use_gpu, config.gpu_id,
|
||||
config.gpu_mem, config.cpu_math_library_num_threads,
|
||||
config.use_mkldnn, config.max_side_len, config.det_db_thresh,
|
||||
config.det_db_box_thresh, config.det_db_unclip_ratio,
|
||||
config.visualize);
|
||||
DBDetector det(
|
||||
config.det_model_dir, config.use_gpu, config.gpu_id, config.gpu_mem,
|
||||
config.cpu_math_library_num_threads, config.use_mkldnn,
|
||||
config.use_zero_copy_run, config.max_side_len, config.det_db_thresh,
|
||||
config.det_db_box_thresh, config.det_db_unclip_ratio, config.visualize);
|
||||
CRNNRecognizer rec(config.rec_model_dir, config.use_gpu, config.gpu_id,
|
||||
config.gpu_mem, config.cpu_math_library_num_threads,
|
||||
config.use_mkldnn, config.char_list_file);
|
||||
config.use_mkldnn, config.use_zero_copy_run,
|
||||
config.char_list_file);
|
||||
|
||||
auto start = std::chrono::system_clock::now();
|
||||
std::vector<std::vector<std::vector<int>>> boxes;
|
||||
|
|
|
@ -32,7 +32,7 @@ void DBDetector::LoadModel(const std::string &model_dir) {
|
|||
|
||||
// false for zero copy tensor
|
||||
// true for commom tensor
|
||||
config.SwitchUseFeedFetchOps(true);
|
||||
config.SwitchUseFeedFetchOps(!this->use_zero_copy_run_);
|
||||
// true for multiple input
|
||||
config.SwitchSpecifyInputNames(true);
|
||||
|
||||
|
@ -61,12 +61,21 @@ void DBDetector::Run(cv::Mat &img,
|
|||
this->permute_op_.Run(&resize_img, input.data());
|
||||
|
||||
// Inference.
|
||||
paddle::PaddleTensor input_t;
|
||||
input_t.shape = {1, 3, resize_img.rows, resize_img.cols};
|
||||
input_t.data = paddle::PaddleBuf(input.data(), input.size() * sizeof(float));
|
||||
input_t.dtype = PaddleDType::FLOAT32;
|
||||
std::vector<paddle::PaddleTensor> outputs;
|
||||
this->predictor_->Run({input_t}, &outputs, 1);
|
||||
if (this->use_zero_copy_run_) {
|
||||
auto input_names = this->predictor_->GetInputNames();
|
||||
auto input_t = this->predictor_->GetInputTensor(input_names[0]);
|
||||
input_t->Reshape({1, 3, resize_img.rows, resize_img.cols});
|
||||
input_t->copy_from_cpu(input.data());
|
||||
this->predictor_->ZeroCopyRun();
|
||||
} else {
|
||||
paddle::PaddleTensor input_t;
|
||||
input_t.shape = {1, 3, resize_img.rows, resize_img.cols};
|
||||
input_t.data =
|
||||
paddle::PaddleBuf(input.data(), input.size() * sizeof(float));
|
||||
input_t.dtype = PaddleDType::FLOAT32;
|
||||
std::vector<paddle::PaddleTensor> outputs;
|
||||
this->predictor_->Run({input_t}, &outputs, 1);
|
||||
}
|
||||
|
||||
std::vector<float> out_data;
|
||||
auto output_names = this->predictor_->GetOutputNames();
|
||||
|
|
|
@ -40,13 +40,21 @@ void CRNNRecognizer::Run(std::vector<std::vector<std::vector<int>>> boxes,
|
|||
this->permute_op_.Run(&resize_img, input.data());
|
||||
|
||||
// Inference.
|
||||
paddle::PaddleTensor input_t;
|
||||
input_t.shape = {1, 3, resize_img.rows, resize_img.cols};
|
||||
input_t.data =
|
||||
paddle::PaddleBuf(input.data(), input.size() * sizeof(float));
|
||||
input_t.dtype = PaddleDType::FLOAT32;
|
||||
std::vector<paddle::PaddleTensor> outputs;
|
||||
this->predictor_->Run({input_t}, &outputs, 1);
|
||||
if (this->use_zero_copy_run_) {
|
||||
auto input_names = this->predictor_->GetInputNames();
|
||||
auto input_t = this->predictor_->GetInputTensor(input_names[0]);
|
||||
input_t->Reshape({1, 3, resize_img.rows, resize_img.cols});
|
||||
input_t->copy_from_cpu(input.data());
|
||||
this->predictor_->ZeroCopyRun();
|
||||
} else {
|
||||
paddle::PaddleTensor input_t;
|
||||
input_t.shape = {1, 3, resize_img.rows, resize_img.cols};
|
||||
input_t.data =
|
||||
paddle::PaddleBuf(input.data(), input.size() * sizeof(float));
|
||||
input_t.dtype = PaddleDType::FLOAT32;
|
||||
std::vector<paddle::PaddleTensor> outputs;
|
||||
this->predictor_->Run({input_t}, &outputs, 1);
|
||||
}
|
||||
|
||||
std::vector<int64_t> rec_idx;
|
||||
auto output_names = this->predictor_->GetOutputNames();
|
||||
|
@ -124,7 +132,7 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
|
|||
|
||||
// false for zero copy tensor
|
||||
// true for commom tensor
|
||||
config.SwitchUseFeedFetchOps(true);
|
||||
config.SwitchUseFeedFetchOps(!this->use_zero_copy_run_);
|
||||
// true for multiple input
|
||||
config.SwitchSpecifyInputNames(true);
|
||||
|
||||
|
|
|
@ -4,6 +4,7 @@ gpu_id 0
|
|||
gpu_mem 4000
|
||||
cpu_math_library_num_threads 10
|
||||
use_mkldnn 0
|
||||
use_zero_copy_run 1
|
||||
|
||||
# det config
|
||||
max_side_len 960
|
||||
|
|
Loading…
Reference in New Issue