Postprocessor object for PaddleDet serials model.
More...
#include <postprocessor.h>
Postprocessor object for PaddleDet serials model.
◆ PaddleDetPostprocessor()
fastdeploy::vision::detection::PaddleDetPostprocessor::PaddleDetPostprocessor |
( |
const std::string & |
arch | ) |
|
|
inlineexplicit |
Create a preprocessor instance for PaddleDet serials model.
- Parameters
-
[in] | config_file | Path of configuration file for deployment, e.g ppyoloe/infer_cfg.yml |
◆ ApplyNMS()
void fastdeploy::vision::detection::PaddleDetPostprocessor::ApplyNMS |
( |
| ) |
|
|
inline |
Apply box decoding and nms step for the outputs for the model.This is only available for those model exported without box decoding and nms.
◆ Run()
bool fastdeploy::vision::detection::PaddleDetPostprocessor::Run |
( |
const std::vector< FDTensor > & |
tensors, |
|
|
std::vector< DetectionResult > * |
result |
|
) |
| |
Process the result of runtime and fill to ClassifyResult structure.
- Parameters
-
[in] | tensors | The inference result from runtime |
[in] | result | The output result of detection |
- Returns
- true if the postprocess successed, otherwise false
◆ SetNMSOption()
void fastdeploy::vision::detection::PaddleDetPostprocessor::SetNMSOption |
( |
const NMSOption & |
option | ) |
|
|
inline |
If you do not want to modify the Yaml configuration file, you can use this function to set NMS parameters.
The documentation for this class was generated from the following files:
- /fastdeploy/my_work/FastDeploy/fastdeploy/vision/detection/ppdet/postprocessor.h
- /fastdeploy/my_work/FastDeploy/fastdeploy/vision/detection/ppdet/postprocessor.cc