12 Commits

Author	SHA1	Message	Date
zhoushunjie	f80775b451	Add clip function	2022-11-23 09:04:25 +00:00
zhoushunjie	1b32381201	Add sqrt, exp, round, log functions	2022-11-23 07:23:05 +00:00
zhoushunjie	5ce0fd29f8	Add maximum functions	2022-11-23 05:14:30 +00:00
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	e93bf6e35c	[Other] Add FDTensor function Pad (#532) ... * Add InferShape func for all the vision processors * fix infer shape of limit short * Fix infer shape bug of stride_pad * revert modify of processor * add function pad	2022-11-08 21:45:31 +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
Wang Xinyu	caa369f64a	[Backend] TRT cast GPU input from int64 to int32, output from int32 to int64, and Windows support building CUDA files (#426) ... * TRT cast int64 to int32 * windows cmake build cuda src * fix windows cmake error when build cuda src * add a notice in windows gpu build doc * cmake add cuda std=11 * TRT cast output from int32 to int64 * nits * trt get original input output dtype	2022-10-28 13:38:06 +08:00
Jack Zhou	9c150f0bfb	Upgrade eigen func (#253) ... * Add FDTensor copy and move assignment and constructor * Upgrade the transpose to receive the output tensor same as input tensor * Add note * Add realloc for FDTensor * Support output equals to input for softmax * Remove FDTensor::Alloc	2022-09-20 10:58:07 +08:00
Jason	68523be411	Modify file structure to separate python and cpp code (#223) ... Modify code structure	2022-09-14 15:44:13 +08:00