23 Commits (0532bc4078f59e44967df2ebca4e2aa0bd28ea36)

Author	SHA1	Message	Date
qingqing01	24509f4af9	Fix the grammar in copyright. (#8403)	9 years ago
tensor-tang	a8eeef86ac	make MKLDNNLayer input grad as a vector	9 years ago
tensor-tang	bc0d255796	make MKLDNNLayer input value as a vector	9 years ago
tensor-tang	c397599dfd	remove weight and bias in MKLDNN reset function, since not all layers have weight and bias. ... and remove some comments.	9 years ago
tensor-tang	a9490a1053	make output channels changeable in reshape function	9 years ago
tensor-tang	2826ccbbd3	remove unused code and fix typo	9 years ago
tensor-tang	aecfeb7257	refine check macro	9 years ago
tensor-tang	5c892db64c	remove unused code ... refine comments and bias fix typo and todo	9 years ago
tensor-tang	9e38dafa29	change MKLDNNMatrix create interface since MatrixPtr is not always required	9 years ago
tensor-tang	c1914543b0	refine mkldnn logic, move reset buffers into MKLDNNLayer	9 years ago
tensor-tang	1199aa6876	fix bug: clear grad and always share data when output has cpu ... and add activation in unit tests	9 years ago
tensor-tang	7a7c8fd9e5	simplify some comments and code	9 years ago
tensor-tang	698071cc33	share mkldnn output value data if next layer is cpu device	9 years ago
tensor-tang	6715beaace	enable merge output grad of mkldnn	9 years ago
Luo Tao	c53d214205	fix compiler warning from MKLDNNLayer and so on	9 years ago
tensor-tang	bea39f6314	add compare simple net of mkldnn and cpu	9 years ago
tensor-tang	ed27a3be78	add some log info	9 years ago
tensor-tang	4ec3a77a43	should run resetBwd before bwdAct	9 years ago
tensor-tang	49d4b39f28	fix typo and remove some unused code	9 years ago
tensor-tang	b0d9b68a5f	unify functions of mkldnn_fc and refine comments	9 years ago
tensor-tang	f2317b67f7	separate resetFwd and resetBwd to some sub functions	9 years ago
tensor-tang	66fdbd0cee	add some comment and simplify some code	9 years ago
tensor-tang	f3a23b6840	add MKLDNNConvLayer	9 years ago