Jack Zhou
d74e1209ae
[Diffusion] Add StableDiffusionInpaint pipeline ( #760 )
...
* Update Inpaint pipeline
* Update concat
* Add GaussianRandomKernel
* Update GaussianRandom
* Add vae endoder
* Add unet infer
* Add vae decoder predict
* add PrepareMaskAndMaskedImage
* Add imwrite
* Add time counter
* Fix pipeline
* use FDTensor move
* Fix scaled_linear dpm solver
* Add RGB2BGR
2022-12-02 19:30:32 +08:00
Jack Zhou
de98163efa
[Functions] Add +-*/ operators and reshape for FDTensor ( #655 )
...
* Add +-*/ functions
* Add same dims test case for operations
* add broadcast 0
* Add broadcast dim2 testcase
* Add broadcast dim3 and dim4 testcase
* Add +-*/ operators
* Add mixed operation
* refresh code style
* Add reshape op
* update code style
2022-11-23 11:34:02 +08:00
Wang Xinyu
a36f5d3396
[Backend] cuda normalize and permute, cuda concat, optimized ppcls, ppdet & ppseg ( #546 )
...
* cuda normalize and permute, cuda concat
* add use cuda option for preprocessor
* ppyoloe use cuda normalize
* ppseg use cuda normalize
* add proclib cuda in processor base
* ppcls add use cuda preprocess api
* ppcls preprocessor set gpu id
* fix pybind
* refine ppcls preprocessing use gpu logic
* fdtensor device id is -1 by default
* refine assert message
Co-authored-by: heliqi <1101791222@qq.com >
2022-11-14 18:44:00 +08:00
Jason
f2fed7959b
[Other] Add namespace for functions ( #538 )
...
Add namespace for functions
2022-11-09 13:57:53 +08:00
Jason
3589c0fa94
[Model] Refactor PaddleClas module ( #505 )
...
* Refactor the PaddleClas module
* fix bug
* remove debug code
* clean unused code
* support pybind
* Update fd_tensor.h
* Update fd_tensor.cc
* temporary revert python api
* fix ci error
* fix code style problem
2022-11-07 19:33:47 +08:00
Jack Zhou
70f664161f
[Functions] Add fd tensor concat ( #507 )
...
* Add fd tensor concat
* fix comment
2022-11-07 10:02:42 +08:00
