apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-27 02:20:31 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[CVCUDA] PaddleDetection preprocessor support CV-CUDA (#1493)

Browse Source 
* ppdet preproc use manager

* pad_to_size chw opencv

* pad_to_size chw flycv

* fix pad_to_size flycv

* add warning message

* cvcuda convert cubic to linear, padToSize cvcuda

* stridedpad cvcuda

* fix flycv include

* fix flycv include

* fix flycv build

* cast cvcuda

* fix pybind

* fix normalize permute cuda

* base processor move funcs to cc

* Update pad_to_size.cc
This commit is contained in:
Wang Xinyu
2023-03-10 12:43:57 +08:00
committed by GitHub
parent 9ee2118e1f
commit cb7c8a07d4
23 changed files with 537 additions and 239 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
fastdeploy/vision/common/processors/cvcuda_utils.cc
View File

@@ -111,6 +111,17 @@ void CreateCvCudaImageBatchVarShape(std::vector<FDTensor*>& tensors,
img_batch.pushBack(CreateImageWrapData(*(tensors[i])));
}
}
NVCVInterpolationType CreateCvCudaInterp(int interp) {
// CV-CUDA Interp value is compatible with OpenCV
auto nvcv_interp = NVCVInterpolationType(interp);
// Due to bug of CV-CUDA CUBIC resize, will force to convert CUBIC to LINEAR
if (nvcv_interp == NVCV_INTERP_CUBIC) {
return NVCV_INTERP_LINEAR;
}
return nvcv_interp;
}
#endif
} // namespace vision