[Model] Yolov5/v5lite/v6/v7/v7end2end: CUDA preprocessing (#370)

* add yolo cuda preprocessing

* cmake build cuda src

* yolov5 support cuda preprocessing

* yolov5 cuda preprocessing configurable

* yolov5 update get mat data api

* yolov5 check cuda preprocess args

* refactor cuda function name

* yolo cuda preprocess padding value configurable

* yolov5 release cuda memory

* cuda preprocess pybind api update

* move use_cuda_preprocessing option to yolov5 model

* yolov5lite cuda preprocessing

* yolov6 cuda preprocessing

* yolov7 cuda preprocessing

* yolov7_e2e cuda preprocessing

* remove cuda preprocessing in runtime option

* refine log and cmake variable name

* fix model runtime ptr type

Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
Wang Xinyu
2022-10-19 16:04:58 +08:00
committed by GitHub
parent 4b3e93223f
commit c8d6c8244e
26 changed files with 752 additions and 24 deletions

View File

@@ -57,7 +57,7 @@ bool FastDeployModel::InitRuntime() {
}
if (is_supported) {
runtime_ = std::unique_ptr<Runtime>(new Runtime());
runtime_ = std::shared_ptr<Runtime>(new Runtime());
if (!runtime_->Init(runtime_option)) {
return false;
}
@@ -107,7 +107,7 @@ bool FastDeployModel::CreateCpuBackend() {
continue;
}
runtime_option.backend = valid_cpu_backends[i];
runtime_ = std::unique_ptr<Runtime>(new Runtime());
runtime_ = std::shared_ptr<Runtime>(new Runtime());
if (!runtime_->Init(runtime_option)) {
return false;
}
@@ -130,7 +130,7 @@ bool FastDeployModel::CreateGpuBackend() {
continue;
}
runtime_option.backend = valid_gpu_backends[i];
runtime_ = std::unique_ptr<Runtime>(new Runtime());
runtime_ = std::shared_ptr<Runtime>(new Runtime());
if (!runtime_->Init(runtime_option)) {
return false;
}