apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-11 19:40:25 +08:00
Code Issues Actions 6 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

6
fastdeploy/vision/classification/ppcls/preprocessor.cc
View File

@@ -138,8 +138,10 @@ bool PaddleClasPreprocessor::Apply(FDMatBatch* image_batch,
}
outputs->resize(1);
(*outputs)[0] = std::move(*(image_batch->Tensor()));
(*outputs)[0].device_id = DeviceId();
FDTensor* tensor = image_batch->Tensor();
(*outputs)[0].SetExternalData(tensor->Shape(), tensor->Dtype(),
tensor->Data(), tensor->device,
tensor->device_id);
return true;
}