“Sheng Su 2015-10-12”版本间的差异
来自cslt Wiki
（以“four GPU training: -- * having tried to change learning rate, mini-batch size and the gap, still diverge. * having tried to use asynchronous way to update, still div...”为内容创建页面） |
（没有差异）
|
2015年10月12日 (一) 12:07的最后版本
four GPU training: --
- having tried to change learning rate, mini-batch size and the gap, still diverge.
- having tried to use asynchronous way to update, still diverge.
- keep going to find the reason of divergency, and going to use some other methods to try.
