apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Backend] support bechmark mode for runtime and backend (#1201)

Browse Source 
* [backend] support bechmark mode for runtime and backend

* [backend] support bechmark mode for runtime and backend

* [pybind11] add benchmark methods pybind

* [pybind11] add benchmark methods pybind

* [Other] Update build scripts

* [Other] Update cmake/summary.cmake

* [Other] update build scripts

* [Other] add ENABLE_BENCHMARK option -> setup.py

* optimize backend time recording

* optimize backend time recording

* optimize trt backend time record

* [backend] optimze backend_time recording for trt

* [benchmark] remove redundant logs

* fixed ov_backend confilct

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] remove use_gpu option from ort backend option

* [benchmark] update benchmark_ppdet.py

* [benchmark] update benchmark_ppcls.py

* fixed lite backend conflicts

* [Lite] fixed lite xpu

* add benchmark macro

* add RUNTIME_PROFILE_LOOP macros

* add comments for RUNTIME_PROFILE macros

* add comments for new apis

* add comments for new apis

* update benchmark_ppdet.py

* afixed bugs

* remove unused codes

* optimize RUNTIME_PROFILE_LOOP macros

* optimize RUNTIME_PROFILE_LOOP macros

* add comments for benchmark option and result

* add docs for benchmark namespace
This commit is contained in:
DefTruth
2023-02-06 14:29:35 +08:00
committed by GitHub
parent 42d14e7119
commit f73a538f61
34 changed files with 741 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/runtime/backends/lite/lite_backend.cc
View File

@@ -100,7 +100,7 @@ bool LiteBackend::InitFromPaddle(const std::string& model_file,
auto shape = tensor->shape();
info.shape.assign(shape.begin(), shape.end());
info.name = output_names[i];
if (!option_.device == Device::KUNLUNXIN) {
if (option_.device != Device::KUNLUNXIN) {
info.dtype = LiteDataTypeToFD(tensor->precision());
}
outputs_desc_.emplace_back(info);
@@ -136,6 +136,8 @@ bool LiteBackend::Infer(std::vector<FDTensor>& inputs,
<< inputs_desc_.size() << ")." << std::endl;
return false;
}
RUNTIME_PROFILE_LOOP_H2D_D2H_BEGIN
for (size_t i = 0; i < inputs.size(); ++i) {
auto iter = inputs_order_.find(inputs[i].name);
if (iter == inputs_order_.end()) {
@@ -143,6 +145,7 @@ bool LiteBackend::Infer(std::vector<FDTensor>& inputs,
<< " in loaded model." << std::endl;
return false;
}
auto tensor = predictor_->GetInput(iter->second);
// Adjust dims only, allocate lazy.
tensor->Resize(inputs[i].shape);
@@ -174,8 +177,10 @@ bool LiteBackend::Infer(std::vector<FDTensor>& inputs,
FDASSERT(false, "Unexpected data type of %d.", inputs[i].dtype);
}
}
RUNTIME_PROFILE_LOOP_BEGIN(1)
predictor_->Run();
RUNTIME_PROFILE_LOOP_END
outputs->resize(outputs_desc_.size());
for (size_t i = 0; i < outputs_desc_.size(); ++i) {
@@ -188,6 +193,7 @@ bool LiteBackend::Infer(std::vector<FDTensor>& inputs,
memcpy((*outputs)[i].MutableData(), tensor->data<void>(),
(*outputs)[i].Nbytes());
}
RUNTIME_PROFILE_LOOP_H2D_D2H_END
return true;
}