56 Commits (28dc9ba3c14edb2b3d8389080ba3ea06f60684c2)

Author	SHA1	Message	Date
wangmeng28	7be4f2b754	Merge remote-tracking branch 'upstream/develop' into img_separable_conv	7 years ago
wangmeng28	94ca8f2152	Make the default layer type for separable conv is exconv	7 years ago
qiaolongfei	964f01e3e8	fix simple_gru2 doc	7 years ago
wangmeng28	126d274ed4	Add separable convolution	7 years ago
Cao Ying	56ec40ad9c	Merge pull request #4924 from ranqiu92/attention ... Add the configuration helper for multi-head attention.	7 years ago
ranqiu	f22402933e	Refine multi_head_attention	7 years ago
ranqiu	81abcdea39	Refine dot_product_attention	7 years ago
ranqiu	06c7686aa1	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into attention	7 years ago
peterzhang2029	e97354152c	unify the bias	7 years ago
peterzhang2029	1b6a54e286	fix error for annotation	7 years ago
ranqiu	7461b35977	Refine multi-head attention	7 years ago
ranqiu	4ad12a0bd5	Fix bugs of dot-product attention	8 years ago
ranqiu	947c528508	Remove redundant flags	8 years ago
ranqiu	4d15b107f3	Add multi-head attention	8 years ago
ranqiu	78320194aa	refine dot-product attention according to the comments	8 years ago
ranqiu	4545a058bd	add dot-product attention	8 years ago
peterzhang2029	fc3b129b08	delete the unused comments	8 years ago
peterzhang2029	bfba756b48	update the version of pre-commit0.13.2	8 years ago
peterzhang2029	9e74b89877	update notation in networks.py roughly	8 years ago
zhangchao41	b90461b9d9	fix the typo of the param description in sequence_conv_pool	8 years ago
chengduo	34f4f763f9	Update networks.py	8 years ago
chengduoZH	f715c740bf	Add_config_parser_for_Conv3D_DeConv3D	8 years ago
zlx	a59fa46c1f	Merge branch 'add_paramAttr' of https://github.com/NHZlX/Paddle into add_paramAttr	8 years ago
zlx	18f4d24d0d	moidify comment of im_conv_group	8 years ago
Zhaolong Xing	5f32cc10c2	Update networks.py ... modify the format	8 years ago
zlx	21a3c9d6f4	add the comments for img_conv_groups	8 years ago
zlx	fae3632c91	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_paramAttr	8 years ago
zlx	a183a80e2e	add param_attr for img_conv_group(...)	8 years ago
caoying03	1b6faffeb5	Merge branch 'develop' into fix_recurrent_parse_bug	8 years ago
caoying03	0ed51ce2e4	fix bug of type check of inputs to recurrent_group.	8 years ago
Yu Yang	62da4a1cde	Merge pull request #2802 from reyoung/feature/fix_python_slow ... Fix slow parsing a recursive depends topology	8 years ago
Yu Yang	313e9f551f	Fix slow parsing a recursive depends topology ... * Fix #2797 * It because trainer_config_helpers' __dfs_travel__ did not record the node which travelled, and if the topology has a recursive dependency, there are some nodes will be travelled multiple times. * Add a `travelled` set to record which node is travelled. * Also add a unittest for this situation.	8 years ago
caoying03	68ec558c21	update the md5sum of WMT14 trained model.	8 years ago
caoying03	5c68aacad1	follow comments.	8 years ago
caoying03	b0ad9c9074	enable intializing memory state for lstmemory_group.	8 years ago
Yu Yang	b34a05d114	Fix travis-ci in new image ... Fix issue #2562	8 years ago
caoying03	692d251869	add missing configuration functions in v2 API.	8 years ago
Yu Yang	3f1151a54c	Add error clipping to MT demo. ... * Compose GRU step naive layer in trainer config helpers. * It is uses mixed_layer for gate. * It supports ERROR_CLIPPING, DROPOUT * Add error clipping in MT demo. * Fix #1143 * Fix #1891	8 years ago
Haonan	781b85b5fc	rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name	8 years ago
emailweixu	c1f9cd9dbe	Merge pull request #1241 from wangyang59/rnnParaShare ... make gru_group parameters sharable	8 years ago
zhanghaichao	e1d074abdb	updated comments for gru_group and lstm_group in networks.py	8 years ago
wangyang59	6da7283475	make gru_group parameters sharable	8 years ago
Yi Wang	e9549cbb78	Change "Baidu, Inc" into "PaddlePaddle Authors"	8 years ago
qijun	a1ba3f442f	format python code in python directory	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
luotao1	652b83478f	remove deprecated start input in img_pool_layer (#237)	9 years ago
Yu Yang	2f82d72ede	Fix bug in yield dictionary in DataProvider. (#197) ... * Fix bug in yield dictionary in DataProvider. * Also make virtualenv work in Paddle.	9 years ago
Yu Yang	e4952ca6ce	Add FAQ (#128) ... * Init commit for doing FAQ * Add speed up training * Add graphviz to ci * Add shared paramter * Tiny refine	9 years ago
qingqing01	191fafe355	support rectangle padding, stride, window and input for PoolProjection (#115) ... * support rectangle padding, stride, window and input for PoolProjection * Follow comments. 1. Remove start 2. refine img_pool_a/b.conf for test_NetworkCompare 3. Split unit test * Modify the test in img_layers.py	9 years ago
Yu Yang	d130d18146	Complete unittest for trainer_config_helpers. (#108) ... * Fix lots of trainer_config_helpers bug, and complete unittest for `layers.py`	9 years ago