- 12 11月, 2016 3 次提交
- 17 10月, 2016 1 次提交
-
-
由 emailweixu 提交于
* Fix sparse training for trainer_count=1 For trainer_count=1, the gradient machine is NeuralNetwork, which does not create parameter buf for PARAMETER_GRADIENT for sparse update in Parameter::enableType. But gradient parameter buf is still used in SgdThreadUpdater. * Minor update to comment
-
- 27 9月, 2016 1 次提交
-
-
由 emailweixu 提交于
* Correctly handling multiple inputs and integer inputs for recurrent_group * Fix ScatterAgentLayer for generation * Revert sequence_(nest)_rnn.conf
-
- 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
- 13 9月, 2016 1 次提交
-
-
由 Yu Yang 提交于
-
- 10 9月, 2016 1 次提交
-
-
由 liaogang 提交于
-
- 08 9月, 2016 1 次提交
-
-
由 Haonan 提交于
Change-Id: Ia60c008a8c922f66e6b5e2ca3e488fc4625d6506
-
- 30 8月, 2016 1 次提交
-
-
由 hedaoyuan 提交于
ISSUE=4586833 git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1429 1ad973e4-5ce8-4261-8a94-b56d1f490c56
-
- 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
-