316 Commits (f22da580fa7bba561ccbfd3ea55fcfbb264bf12a)

Author	SHA1	Message	Date
caoying03	075954c17c	follow comment.	9 years ago
caoying03	dc60671127	Merge branch 'develop' into enable_error_clipping_for_fc	9 years ago
caoying03	203364281e	enable error clipping in FC layer.	9 years ago
wanghaoshuang	d378e0a0cd	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer	9 years ago
Tao Luo	7f380c1be3	Merge pull request #2701 from luotao1/stride ... stride pooling for max and average layer	9 years ago
wanghaoshuang	5e6e1f636a	Add grad test and python wrapper for crop layer	9 years ago
Yang yaming	312ce8b419	Merge pull request #2497 from pkuyym/ssd_outloss ... Add DetectionOutputLayer and MultiBoxLossLayer.	9 years ago
zlx	211f83fa22	set depthwise conv layer interface in python	9 years ago
Luo Tao	0e61730039	stride pooling for max and average layer	9 years ago
dangqingqing	0c70f34c60	Fix bug for flowers dataset and row_conv.	9 years ago
yangyaming	b5ab4b69bc	Follow comments, mainly use std::copy to simplify logic.	9 years ago
lianxiaochen	5e87e27c75	fix error clipping	9 years ago
zlx	561c4562cf	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning	9 years ago
Yang yaming	f551c271af	Merge pull request #2467 from pkuyym/ssd_map ... Add DetectionMAPEvaluator	9 years ago
zlx	15bf6e05b5	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning	9 years ago
xuwei06	61222578b4	Allow printer layer to print user provided message ... For example: layer.printer(input=[x, y], format="x=%s y=%s")	9 years ago
qingqing01	8266546eb2	Merge pull request #2480 from emailweixu/repeat_layer ... Repeat layer for column vector	9 years ago
yangyaming	65969dad64	Add DetectionOutputLayer and MultiBoxLossLayer.	9 years ago
xuwei06	226f810352	Add activiation for repeat_layer ... Also remove active_type argument for many layers in config_parser.py because it is automatically handled by LayerBase.	9 years ago
xuwei06	ef61288f9e	Clean-up recurrent group related python code ... No longer need to specify target_inlinks or is_seq.	9 years ago
xuwei06	fc0ad9048a	Repeat layer for column vector	9 years ago
xuwei06	17994e38aa	RecurrentGroup with mixed input sequence types ... No longer need to use SubsequenceInput. The framework will detect.	9 years ago
yangyaming	2207659250	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into ssd_map	9 years ago
zlx	6248e566f9	merge from remote	9 years ago
xuwei06	dd2cbb63bf	Parameter initializer in V2 API ... User can provide an initializer in ParamAttr. The initializer will be called when at parameters.create().	9 years ago
xzl	23b1a27483	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning	9 years ago
xzl	997cef2e63	tiny modify	9 years ago
yangyaming	597a58c3ef	Add DetectionMAPEvaluator.	9 years ago
xzl	97a2fde995	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning	9 years ago
qingqing01	6bc9277503	Merge branch 'develop' into row_conv	9 years ago
caoying03	892b1f9ff6	Merge branch 'develop' into fix_config_parsing_bug	9 years ago
dangqingqing	37015fadbd	update code	9 years ago
caoying03	c7483bf956	add configuration helper for prelu layer.	9 years ago
caoying03	692d251869	add missing configuration functions in v2 API.	9 years ago
dangqingqing	18cd1f2558	Fix bug and Python API.	9 years ago
xzl	18435f2a73	modify the pruning from reading mask to specify sparsity_ratio	9 years ago
xzl	ca55a24eb3	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning	9 years ago
xzl	5413af8d11	imporve pruning module	9 years ago
xuwei06	97c4d23fab	Add docs and clean up unused code	9 years ago
xuwei06	7d0355cdd0	Fix V2 API	9 years ago
Yibing Liu	2e4c0bd2ea	enable global gradient_clipping_threshold ... correct a typo optimize code fix a bug	9 years ago
Luo Tao	23e00ba379	follow comments	9 years ago
dangqingqing	3c5e0f8a5d	remove g_pass_height_width in config_parse.py	9 years ago
dangqingqing	1fd00758ac	SmoothL1 loss	9 years ago
Luo Tao	d369577fed	add reversed poolSequenceWithStride	9 years ago
Luo Tao	0291c01884	Merge branch 'develop' into stride	9 years ago
Tao Luo	5961b52b13	Merge pull request #1653 from Noplz/normalize-layer ... CrossChannelNorm Layer for SSD	9 years ago
Luo Tao	9298a9ec0d	stride pooling for seqlastin and seqfirstin	9 years ago
wangyang59	ec7184ac18	fixed a bug in conv_projection issue #1681	9 years ago
wangyang59	090c974e4b	completed implementation of cudnn_convt convTransProjection and convTransOperator	9 years ago
wangyang59	07c1ea258f	python interface for convTransProjection and convTransOperator	9 years ago
Yuan Gao	8c2d1bad7a	Merge branch 'develop' into normalize-layer	9 years ago
gaoyuan	eb43d93a58	Change Normalize layer to CrossChannelNorm layer	9 years ago
Yu Yang	bd4ec1b493	Merge branch 'develop' into memory.set_input	9 years ago
Peng Li	03889bab6f	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	9 years ago
Tao Luo	4375a64ea1	fix bug to pass travis	9 years ago
Peng Li	bf838034d6	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	9 years ago
gaoyuan	eea0097dcb	NormalizeLayer for SSD	9 years ago
LCY-Seso	1d58949a40	Merge branch 'develop' into enable_drop_in_average_and_max_layer	9 years ago
Liang Zhao	e768721cd9	fix calculating totalScore2_ bug	9 years ago
xuwei06	7d551dd484	Make it possible to postpone setting the layer name for a memory. ... The reason for adding the function is exemplified in the following hypothetical code: mem = memory(name=None, size=256) hidden = fc_layer(input=mem) state = hidden + x mem.set_input(state) In the above code segment, it would be very annoying if we require the user to provide the name at memory() call because the layer name of state is automatically generated and is not easy to set it. Change-Id: I918bf1d3d5c26addd88a6f7021e98b3e0e9df494	9 years ago
wangkuiyi	ccb553fec4	Merge pull request #1253 from wangkuiyi/python_learning_and_refactor ... Rename Python function DataBase into create_data_config_proto	9 years ago
Yi Wang	b8f3a5c433	Correct the wrong deletion of a single character	9 years ago
王益	b36df98d01	Correct Python identation	9 years ago
Yi Wang	058eeac0fc	Revert "Remove completely create_data_config_proto" ... This reverts commit ab279beed1.	9 years ago
Yi Wang	ab279beed1	Remove completely create_data_config_proto	9 years ago
Yi Wang	996b1de1d8	Rename DataBase into create_data_config_proto	9 years ago
Haonan	6245fed240	rotate_layer python interface fixes	9 years ago
Haonan	55eb2fcffa	format correction	9 years ago
Haonan	781b85b5fc	rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name	9 years ago
wangyang59	04b5daf92d	change the parameter position of gru_step_layer from 1 back to 0	9 years ago
wangyang59	6da7283475	make gru_group parameters sharable	9 years ago
dangqingqing	8d47499e1d	update code	9 years ago
zhangruiqing01	19cb2a7fb3	fix default value of cos_sim scale	9 years ago
dangqingqing	6b61a096e1	Optional padding mode, namely ceil or floor, ceil by default.	9 years ago
dangqingqing	8b5431d5e1	padding operation	9 years ago
caoying03	cbbad4202a	delete the modification of SlopeInterceptLayer.	9 years ago
caoying03	08a817e3fb	delete unnecessary parameters and modifications for some mathmatical ... layers.	9 years ago
caoying03	ce939b30ba	enable dropout rate in several computation layers.	9 years ago
caoying03	15a6252f8e	Merge branch 'develop' into enable_drop_in_average_and_max_layer	9 years ago
caoying03	e022c065d7	enable dropout in average and max layer.	9 years ago
qiaolongfei	843b63bb84	add config_parser in trainer_config_helpers to seperate trainer config	9 years ago
qingqing01	b53bdcdc67	Merge pull request #867 from Noplz/ssd ... priorbox layer for Single Shot Multibox Detection Network	9 years ago
Peng Li	b063b0c405	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	9 years ago
Peng Li	af820fb2eb	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	9 years ago
dangqingqing	e4c492d3b8	change type to bool.	9 years ago
dangqingqing	5bb29ece7f	close log info in BN.	9 years ago
dangqingqing	f4f0f2daeb	Fix bug in config_parse.py when batch_norm layer is used in RecurrentLayerGroup.	9 years ago
Peng Li	f1e31ecada	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	9 years ago
Peng Li	8fe3a3aa73	Add excluded_chunk_types to ChunkEvaluator ... The chunks of types in excluded_chunk_types will not be counted in ChunkEvaluator. This is useful for tasks such as SRL, in which chunks of type V (verb) will not be taken into account in evaluation.	9 years ago
gaoyuan	9f990d9059	Add unittest of the priorbox layer	9 years ago
wangyang59	454a1a2912	fixed a bug for demo/gan caused by batchNormLayer	10 years ago
gaoyuan	1048aee0f7	Add input layer check	10 years ago
gaoyuan	707a9c9bbd	Fix variable name and add the annotation	10 years ago
gaoyuan	c0076084e2	Format the python file.	10 years ago
yuan	0eac399280	priorbox layer for ssd	10 years ago
Yu Yang	4afaaa4b92	Autoformat all files	10 years ago
Yu Yang	b6aca330a2	Merge pull request #764 from emailweixu/multiple_parse ... Correctly handling multiple calls to parse_config()	10 years ago
Yi Wang	e9549cbb78	Change "Baidu, Inc" into "PaddlePaddle Authors"	10 years ago
xuwei06	3cf7337f30	Correctly handling multiple calls to parse_config() ... To solve this, we maintain the list of DefaultNameFactory used in by trainer_config_helper, and reset the state at the beginning of each parse_config call. Change-Id: I13c7574dc8f0b6bc6f6b7c92eb425e2c52c926e8	10 years ago
Yiqun Liu	4823075f95	Merge pull request #651 from Xreki/warpctc ... Integrate warp-ctc as WarpCTCLayer, including unit test and layer interface.	10 years ago
Luo Tao	16bebc4388	some tiny fix	10 years ago
Liu Yiqun	78bdd32471	Merge branch 'develop' into warpctc	10 years ago
hanchao	7c76d0eeac	config_parser new feature at ISSUE #726	10 years ago
Luo Tao	7830893a83	fix conflict	10 years ago
Peng Li	1242e7944b	Merge branch 'develop' into fix-crf-weight-and-coeff-bug	10 years ago
Liu Yiqun	25f1fbc491	Merge branch 'develop' into warpctc	10 years ago
Peng Li	d60d34ef3f	Fix bug in python/paddle/trainer/config_parser.py ... The dims for crf and crf_decoding layers are wrong, i.e. height and width are swapped.	10 years ago
wangyang59	09a5b8bd4d	consolidate img_conv.conf in test_NetworkCompare	10 years ago
Luo Tao	1d1a04c033	follow comments on rectangle CNN	10 years ago
Liu Yiqun	4d487c6f35	Integrate warp-ctc as WarpCTCLayer, including unitest and layer interface.	10 years ago
Luo Tao	7573205c68	follow comments on config_parser	10 years ago
Luo Tao	96615fe329	merge develop, fix conflict	10 years ago
dangqingqing	1a8fcc00de	fix the code style	10 years ago
dangqingqing	86060772ed	Merge branch 'develop' of https://github.com/baidu/Paddle into config_parse_bug_fix	10 years ago
dangqingqing	4ca9c3955e	minor changes	10 years ago
dangqingqing	876fa1935d	Fix the config_parse.py if user does not set padding in the old config.	10 years ago
Luo Tao	496d64ebdb	Support rectangle input for CNN	10 years ago
Yu Yang	9115ab1c11	Merge pull request #450 from reyoung/feature/pre-commit-hooks-scripts ... Feature/pre commit hooks scripts	10 years ago
xuwei06	bf6f690f31	Add ScalingProjection ... out = w * input where w is a parameter of size 1 Change-Id: Ife682d62323ceb1a20cbbf6269421b20a862d888	10 years ago
Yu Yang	836d61382f	Update pre-commit-config ... * Check all files by pre commit hooks	10 years ago
qijun	a1ba3f442f	format python code in python directory	10 years ago
Tao Luo	ca0bb40c6e	Merge pull request #300 from QiJune/feature/sppnet ... add SpatialPyramidPoolLayer c++ support	10 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	10 years ago
Tao Luo	eb3bf9ea64	Merge pull request #360 from emailweixu/sum_cost ... Add SumCost	10 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	10 years ago
qijun	9dd588b414	fix merge conflicts	10 years ago
gangliao	8295eb91bf	Merge pull request #287 from gangliao/bilinear ... Add bilinear interpolation layer	10 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	10 years ago
wangyang59	1c58e27fdc	fixed a bug in parse_conv in config_parser.py	10 years ago
wangyang59	af7a50c0d4	minor changes on deconv implementation and add protostr test for deconv layer	10 years ago
wangyang59	53e1629a43	Refactored imageSize in ConvBaseLayer to MathUtil	10 years ago
wangyang59	7a322df0a8	deconv implementation mionr changes in ConvBaseLayer.cpp and config_parser.py	10 years ago
wangyang59	d116b17f06	fix a small bug in ConvTransLayerBase in config_parser.py	10 years ago
wangyang59	fb20187aaa	deconv layer implementation modification following luotao1 comments	10 years ago
wangyang59	3d72e94939	rebase deconv implementation with develop branch and resolve conflicts with pull#218 commit 45c81a414f	10 years ago
wangyang59	5e4cc241ac	Revised deconv implementations according to luotao1	10 years ago
wangyang59	bda259bb18	added more test on convTrans layer and comments	10 years ago
wangyang59	70e44732c2	added convTrans test and python components	10 years ago
qijun	db569f293e	fix merge conflict	10 years ago
qijun	5ece5c96ad	add python wrap for sppLayer	10 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	10 years ago
liaogang	5a1e7dbc6a	Fix conflict	10 years ago
luotao1	e802471c58	abstract outputSize function in CNN-related layers (#314)	10 years ago
liaogang	bd38facada	Fix conflict	10 years ago
liaogang	57348806b5	Follow comments	10 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	10 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.	10 years ago
liaogang	fd4eeaf59c	Merge conflict with maxout layer	10 years ago
liaogang	ddfff3a7fd	Add bilinear interpolation layer	10 years ago
luotao1	3dd8c9bea4	add maxout layer, including interface and unittest (#229) ... * add maxout layer, including interface and unittest * follow maxout comments * auto setting channels * fix unittest bug in test_RecurrentGradientMachine	10 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.	10 years ago
Zrachel	6d21ecef54	add cost_type constraint to weighted_cost interface (#206)	10 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	10 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`	10 years ago
luotao1	8e957df4b2	fix bug in dotmul_operator's api and anotation (#99) ... * fix bug in dotmul_operator's api and anotation * update rnn document * remove redundant info of projection and operator in layers.py	10 years ago
Haonan	b130ba7328	fixed bugs in conv_operator; add calc_output_size (#101)	10 years ago
Yu Yang	2c5a6ac095	Optional fields to shrink generated proto size (#93) ... * remove unnecessary field set in ParameterConfig, Evaluators, etc	10 years ago
Haichao-Zhang	159dd8331c	split dotmul_projection and dotmul_operator (#87) ... * split dotmul_projection and dotmul_operator * bug fix in outputsize checking for mixed layer	10 years ago
xuwei06	05a97ab50e	Further fix the memory for Hierarchical RNN ... Sequences should be sorted according to the number of subsequences they have.	10 years ago
Yu Yang	c7762da330	Merge branch 'master' into merge_icode	10 years ago
zhangruiqing01	699d5f2638	modify RecurrentGradientMachine to support unequal length inputs ... * modify RecurrentGradientMachine to support hasSubSeq sequence inlinks with the same number of sentence but different number of tokens for each sentence Change-Id: Ic71f00a4bb346b4fa93e650dfb4b1a0d8d2338b0	10 years ago
xuwei06	7481429f99	Change cos_sim to use CosSimLayer layer when size=1 and rename convex_comb_layer to linear_comb_layer ... Also add an unittest for layers.py, currently for a few things. More need to be added later.	10 years ago
qingqing01	7dbc092c87	fix cudnn version number for batch norm. (#71) ... * fix CUDNN_VERSION for backward of CudnnBatchNormLayer * fix cudnn version number for BatchNorm	10 years ago
Haonan	6a873f505f	fix the layer name error when stacking RecurrentGroups ... * the last layer in the stack already has all the suffixes	10 years ago
zhangjinchao01	b72beee4f0	fix dash and space bug, ... ISSUE=4586495 git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1408 1ad973e4-5ce8-4261-8a94-b56d1f490c56	10 years ago