108 Commits (ca0bb40c6e4cf90a254c5b82ee82268936817b75)

Author	SHA1	Message	Date
Tao Luo	ca0bb40c6e	Merge pull request #300 from QiJune/feature/sppnet ... add SpatialPyramidPoolLayer c++ support	9 years ago
Luo Tao	aa560dbb97	fix bug in sum_cost	9 years ago
Haonan	ebb153b067	Merge pull request #416 from yu239/hl_activetype ... change the act.name for LinearActivation() to "linear" so that it won't fail in hl_activetype; also fix the hasinputsset in submodel	9 years ago
Tao Luo	eb3bf9ea64	Merge pull request #360 from emailweixu/sum_cost ... Add SumCost	9 years ago
Haonan	45f6e1abee	change hlactivetype instead of act.name	9 years ago
xuwei06	36fa251756	'*' operator overload for LayerOutput ... Making '*' support the multiplication between a scalar and LayerOutput Also changing '+' to support adding between a vector and a scalar. Change-Id: I7daf35590dc2b2f855a29d9ef43ac57979442e0f	9 years ago
qijun	9dd588b414	fix merge conflicts	9 years ago
gangliao	8295eb91bf	Merge pull request #287 from gangliao/bilinear ... Add bilinear interpolation layer	9 years ago
qingqing01	cfc965d52c	Merge pull request #269 from wangyang59/deconv	9 years ago
qijun	61444d903d	Merge remote-tracking branch 'baidu/develop' into feature/sppnet	9 years ago
Haonan	880774d141	change the act.name for LinearActivation() to "linear" so that it won't ... fail in hl_activetype; also fix the hasinputsset in submodel	9 years ago
Haonan	8d4c453bbb	set mixedlayer output size according to input operator (#414) ... * set mixedlayer output size according to input operator * change from num_channel to num_channels for conv_operator (the old one is really misleading because all the others are num_channels) * also changed the arg name in projections.py	9 years ago
liaogang	9ff0db37fe	Generate bilinear protostr via Linux	9 years ago
wangyang59	1c58e27fdc	fixed a bug in parse_conv in config_parser.py	9 years ago
wangyang59	af7a50c0d4	minor changes on deconv implementation and add protostr test for deconv layer	9 years ago
wangyang59	53e1629a43	Refactored imageSize in ConvBaseLayer to MathUtil	9 years ago
wangyang59	03f4b1d4d2	minor changes on deconv per luotao1 comments	9 years ago
wangyang59	7a322df0a8	deconv implementation mionr changes in ConvBaseLayer.cpp and config_parser.py	9 years ago
wangyang59	d116b17f06	fix a small bug in ConvTransLayerBase in config_parser.py	9 years ago
wangyang59	fb20187aaa	deconv layer implementation modification following luotao1 comments	9 years ago
wangyang59	3d72e94939	rebase deconv implementation with develop branch and resolve conflicts with pull#218 commit 45c81a414f	9 years ago
wangyang59	5e4cc241ac	Revised deconv implementations according to luotao1	9 years ago
wangyang59	bda259bb18	added more test on convTrans layer and comments	9 years ago
wangyang59	70e44732c2	added convTrans test and python components	9 years ago
qijun	f173341fb2	Merge remote-tracking branch 'baidu/develop' into feature/sppnet	9 years ago
liaogang	c8091ad80f	Follow comments	9 years ago
liaogang	4dada9c7ce	Delelte old protostr	9 years ago
liaogang	93dc44c9df	Update	9 years ago
liaogang	0519cc6423	Merge branch 'develop' of https://github.com/baidu/Paddle into bilinear	9 years ago
luotao1	e6c83f4ec0	some tiny fixs (#406) ... * some tiny fixs * use VLOG(3)	9 years ago
qijun	eaf3dec9c5	follow comments	9 years ago
liaogang	fd94e6aff8	Merge branch 'develop' of https://github.com/baidu/Paddle into bilinear	9 years ago
qijun	3553576e6e	Merge remote-tracking branch 'baidu/develop' into feature/sppnet	9 years ago
qijun	e2c0713589	follow comments	9 years ago
luotao1	65af9f9495	modify the format of diff information in protostr (#398)	9 years ago
liaogang	db1757556e	Follow comments	9 years ago
qijun	db569f293e	fix merge conflict	9 years ago
qijun	5ece5c96ad	add python wrap for sppLayer	9 years ago
xuwei06	38764bf908	Add sum_cost to document ... And rebase Change-Id: I7ea234b3aa8fc70675af15d91db08242c43fb5ff	9 years ago
xuwei06	ebad8e525d	Add SumCost ... This allows user to implement any type of cost by summing over the output of non-cost layers. Change-Id: Ic55aaabbf0c1299e70b8e48a0effcc91f8f5bd29	9 years ago
liaogang	5a1e7dbc6a	Fix conflict	9 years ago
luotao1	e802471c58	abstract outputSize function in CNN-related layers (#314)	9 years ago
liaogang	91a4064e35	Follow comments	9 years ago
liaogang	bd38facada	Fix conflict	9 years ago
liaogang	57348806b5	Follow comments	9 years ago
wenboyang	c64cd6feb4	Use diff to compare config unittest (#363) ... Fix #342	9 years ago
emailweixu	6c3a678c9a	Add elementwise math operations (#343) ... * Add elementwise math operations This allows use to use expressions like: y=log(1+exp(x)) Also added unittests for ActivationFunction * Enforce keyword arguments for non-positional arguments * Add LogActivation to doc	9 years ago
qingqing01	45c81a414f	Add job=time in trainer, refine cudnn_conv to reduce gpu memory and speed up training. (#218) ... * Add benchmark for PaddlePaddle, tensorflow and caffe * ConvProjection to reduce memory for goolenet * Add unit test for ConvProjection. 1. unit test in test_LayerGrad. 2. compare the ConvPorjection and CudnnConvLayer, also compare the concat_layer+img_conv_layer and concat_layer_conv_projection. * Reduce cudnn_conv memory and add benchmark document. 1. Use TmpMatrix as the workspace in cudnn_conv to reduce gpu memory. It reduce lots of memory. 2. Add benchmark document. 3. fix smallnet_mnist_cifar.py in paddle. * Add job=time and refine cudnn_conv to reduce gpu memroy and speed up * Refine cudnn_conv and shared biases operation in concat_layer and mixed_layer. * follow comments * follow comments * Use unique_ptr to prevent memory leaks in CudnnConvLayer.	9 years ago
liaogang	fd4eeaf59c	Merge conflict with maxout layer	9 years ago
liaogang	ddfff3a7fd	Add bilinear interpolation layer	9 years ago