FastDeploy
latest
Fast & Easy to Deploy!
|
ProcessorManager for Preprocess. More...
#include <manager.h>
Public Member Functions | |
void | UseCuda (bool enable_cv_cuda=false, int gpu_id=-1) |
Use CUDA to boost the performance of processors. More... | |
bool | Run (std::vector< FDMat > *images, std::vector< FDTensor > *outputs) |
Process the input images and prepare input tensors for runtime. More... | |
virtual bool | Apply (FDMatBatch *image_batch, std::vector< FDTensor > *outputs)=0 |
Apply() is the body of Run() function, it needs to be implemented by a derived class. More... | |
ProcessorManager for Preprocess.
|
pure virtual |
Apply() is the body of Run() function, it needs to be implemented by a derived class.
[in] | image_batch | The input image batch |
[in] | outputs | The output tensors which will feed in runtime |
Implemented in fastdeploy::vision::ocr::RecognizerPreprocessor, fastdeploy::vision::ocr::ClassifierPreprocessor, fastdeploy::vision::detection::PaddleDetPreprocessor, fastdeploy::vision::classification::PaddleClasPreprocessor, and fastdeploy::vision::ocr::DBDetectorPreprocessor.
bool fastdeploy::vision::ProcessorManager::Run | ( | std::vector< FDMat > * | images, |
std::vector< FDTensor > * | outputs | ||
) |
Process the input images and prepare input tensors for runtime.
[in] | images | The input image data list, all the elements are returned by cv::imread() |
[in] | outputs | The output tensors which will feed in runtime |
void fastdeploy::vision::ProcessorManager::UseCuda | ( | bool | enable_cv_cuda = false , |
int | gpu_id = -1 |
||
) |
Use CUDA to boost the performance of processors.
[in] | enable_cv_cuda | ture: use CV-CUDA, false: use CUDA only |
[in] | gpu_id | GPU device id |