- 17 10月, 2016 1 次提交
-
-
由 Zrachel 提交于
-
- 09 10月, 2016 1 次提交
-
-
由 qingqing01 提交于
* 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
-
- 28 9月, 2016 1 次提交
-
-
由 Yu Yang 提交于
* Fix lots of trainer_config_helpers bug, and complete unittest for `layers.py`
-
- 22 9月, 2016 1 次提交
-
-
由 luotao1 提交于
* fix bug in dotmul_operator's api and anotation * update rnn document * remove redundant info of projection and operator in layers.py
-
- 21 9月, 2016 1 次提交
-
-
由 Haonan 提交于
-
- 20 9月, 2016 3 次提交
-
-
由 Yu Yang 提交于
* remove unnecessary field set in ParameterConfig, Evaluators, etc
-
由 Haichao-Zhang 提交于
* split dotmul_projection and dotmul_operator * bug fix in outputsize checking for mixed layer
-
由 Yu Yang 提交于
* min_pool_size would be infinite by default. * add unittest for min_pool_size * Fix bug in can_over_batch_size * add unittest for can_over_batch_size * Add DEFINE_PROVIDER_EX * Add default value of should_shuffle * When training, the default value of should_shuffle is True. * When testing, the default value of should_shuffle is False. * User a set a provider should_shuffle or not by pass it to `@provider` * should_shuffle can handle a list of value, not just boolean * Add input order mapping by using name * Add unittest * Add check to check input format. * Default is close for speed reason. * User could stop train when check error, or continue train without this train sample. * use deque instead of vector in generators pool, make erase generator faster. * Add chinese/english documentation * Make should shuffle = false in unittest * Add python files to depends.
-
- 17 9月, 2016 1 次提交
-
-
由 xuwei06 提交于
Sequences should be sorted according to the number of subsequences they have.
-
- 14 9月, 2016 3 次提交
-
-
由 zhangruiqing01 提交于
* modify RecurrentGradientMachine to support hasSubSeq sequence inlinks with the same number of sentence but different number of tokens for each sentence Change-Id: Ic71f00a4bb346b4fa93e650dfb4b1a0d8d2338b0
-
由 xuwei06 提交于
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.
-
由 qingqing01 提交于
* fix CUDNN_VERSION for backward of CudnnBatchNormLayer * fix cudnn version number for BatchNorm
-
- 08 9月, 2016 1 次提交
-
-
由 Haonan 提交于
* the last layer in the stack already has all the suffixes
-
- 29 8月, 2016 1 次提交
-
-
由 zhangjinchao01 提交于
ISSUE=4586495 git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1408 1ad973e4-5ce8-4261-8a94-b56d1f490c56
-