Paddle

Commit Graph

Author	SHA1	Message	Date
zchen0211	2edb69a789	with in-place option	8 years ago
zchen0211	a88901109b	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop	8 years ago
zchen0211	161a15f055	gradient check	8 years ago
qingqing01	fe480b9ebe	Merge branch 'develop' into lookup_table	8 years ago
dangqingqing	f188e22b33	Remove set functor and add comapre_grad test	8 years ago
Yu Yang	d3f219aa99	Change IdentityOp to ScaleOp	8 years ago
qingqing01	c68bfc30a8	Merge pull request #3476 from qingqing01/bp_test Compare the gradient consistency between GPU and CPU calculations	8 years ago
dangqingqing	5181aefc6b	tune max relative error for sigmoid op unit test.	8 years ago
dangqingqing	a28a5564d2	add more comments and fix code style.	8 years ago
Yu Yang	f15e083098	Remove std::shared_ptr in Python & C++ * Also simplify pybind implementation by using OperatorBase as holder type.	8 years ago
dangqingqing	9a0eedf5d4	fix bug.	8 years ago
dangqingqing	84d6434d53	Compare the gradient consistency between GPU and CPU calculations.	8 years ago
Yu Yang	610a25844f	Fix all unit tests in Python	8 years ago
qiaolongfei	f485a9bc50	add auto gradient check design doc	8 years ago
Yu Yang	f0a85b0805	Rename __is_close -> assert_is_close()	8 years ago
Yu Yang	c957445c72	A better error message for gradient checker * Give which parameter, which element are wrong. And what max_diff is.	8 years ago
Qiao Longfei	e31a469ee0	add gradient test framework (#3226 ) * init grad op checker * can run * add GradeChecker class * use get_numeric_gradient * refine code * add softmax and cross entropy auto grad test * use close to judge op_grad and numeric_grad * add cpu and gpu compare * add comments * add support_gpu * fix allclose * fix name error and symplify code * optimize gradient checker * add test_cross_entropy_op * update gradient_checker.py * optimize code * use random.uniform instead of random.random * fix type bug * optimize check_grad * put SupportGPU into OperatorBase * typo	8 years ago
Yu Yang	89d33ff83f	Complete chagne op creation method. Currently use `Operator("fc", X="x", W='w1', B='b1')` as operator creation method. Fix #3198	8 years ago
Yu Yang	133541ee41	Merge codes	8 years ago
Yu Yang	a0590004ce	Add __all__ in `gradient_checker.py`	8 years ago
Yu Yang	fcc28ccea2	Add comments	8 years ago
Yu Yang	7c42aad412	Initialize Gradient Checker Add get_numeric_gradient API and its unittest.	8 years ago

22 Commits (2edb69a7891c63c1d1e8c760e53eed0c3537dfbf)