- 20 6月, 2017 2 次提交
-
-
由 xuwei06 提交于
Make the evaluators inside a recurrent goup true evaluator, meaning that their evaluation results are incorporated into the whole evaluator result.
-
由 xuwei06 提交于
1. v2.layer.parse_network does not correctly handle the generation output. 2. GatherAgentLayer does not correctly handle generation output when batch_size > 1 3. Fix CustomStackTrace for rnn group
-
- 16 6月, 2017 1 次提交
-
-
由 xuwei06 提交于
No longer need to use SubsequenceInput. The framework will detect.
-
- 02 5月, 2017 1 次提交
-
-
由 liaogang 提交于
-
- 21 12月, 2016 1 次提交
-
-
由 Yu Yang 提交于
-
- 12 12月, 2016 1 次提交
-
-
由 Yu Yang 提交于
-
- 09 12月, 2016 1 次提交
-
-
由 Yi Wang 提交于
-
- 22 11月, 2016 1 次提交
-
-
由 Luo Tao 提交于
-
- 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 2 次提交
-
-
由 xuwei06 提交于
Change-Id: I8e0a8ea6fc2760652d9c76440a539c90860062d3
-
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
-
- 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
-