apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-17 22:21:48 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[Backend] Enable TensorRT BatchedNMSDynamic_TRT plugin (#449)

Browse Source 
* Enable TensorRT EfficientNMS plugin

* remove some temporary code

* Update trt_backend.cc

* Update utils.h
This commit is contained in:
Jason
2022-11-04 11:46:29 +08:00
committed by GitHub
parent 7150e6405c
commit 9fa612c24b
8 changed files with 36 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/runtime.h Executable file → Normal file
View File

@@ -338,12 +338,6 @@ struct FASTDEPLOY_DECL RuntimeOption {
std::string model_file = ""; // Path of model file
std::string params_file = ""; // Path of parameters file, can be empty
ModelFormat model_format = ModelFormat::AUTOREC; // format of input model
// inside parameters, only for inside usage
// remove multiclass_nms in Paddle2ONNX
bool remove_multiclass_nms_ = false;
// for Paddle2ONNX to export custom operators
std::map<std::string, std::string> custom_op_info_;
};
/*! @brief Runtime object used to inference the loaded model on different devices