Paddle

Commit Graph

Author	SHA1	Message	Date
qingqing01	80d2e66f9e	Update backward appending stragety to support double backward and fix some bug. (#18104 ) * Update backward.py: - If there is no input grad var in all outputs of previous ops, do not append this op into graph. - Only apply this stragety when double backward. * Update some double backward op. * Update sum_op to judge whether a tensor is empty by numel or IsInitialized().	6 years ago
lvmengsi	5d1ac41b00	Double backward reduce mean (#17372 ) * test=develop, double backward reduce_mean * add comment. test=develop * fix format. test=develop * rename GradGrad -> DoubleGrad. test=develop * fix op_use_default_grad_op_maker.spec. test=develop	6 years ago
zhoukunsheng	bb8ea1637d	fix 16823: delete default_grad register for reduce_all, reduce_any	6 years ago
zhoukunsheng	2d6b4f23f0	test=develop bug fix: reduce_all, reduce_any register GRAD_OP, but have not defined GradKernel	6 years ago
zhoukunsheng	664c342ca0	test=develop split reduce_all_any_op.h into two files add unit test for reduce_all, reduce_any	6 years ago
zhoukunsheng	2c3e4c1888	test=develop add reduce_all, reduce_any op	6 years ago
peizhilin	55510744b5	test=develop	6 years ago
peizhilin	061299be87	fix dependency test=develop	6 years ago
Wu Yi	a2d9b34417	Refine operator cmake (#14413 ) * wip simplify operator framework * wip * wip * done test=develop * clean test=develop * fix test=develop * fix deps test=develop * fix cpu build test=develop * fix tensorrt build test=develop * fix tests test=develop * fix test=develop * fix cpu build test=develop	7 years ago

9 Commits (189b08dc0df0b72530943e33609fe552d376c27e)