“Chao Xing 2016-02-01”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“LAST WEEK ---- Done: *Multi-task transfer learning during transfer-step pre-train. *Find some strategies among each hyper-parameters. **Steps determine the train pa...”为内容创建页面)
 
 
第2行: 第2行:
 
----
 
----
 
Done:
 
Done:
*Multi-task transfer learning during transfer-step pre-train.
+
*Multi-task transfer learning during transfer step pretrain.
 
*Find some strategies among each hyper-parameters.  
 
*Find some strategies among each hyper-parameters.  
 
**Steps determine the train parameters information content, which means larger steps need larger iterations and larger learning rate.
 
**Steps determine the train parameters information content, which means larger steps need larger iterations and larger learning rate.

2016年2月1日 (一) 02:21的最后版本

LAST WEEK


Done:

  • Multi-task transfer learning during transfer step pretrain.
  • Find some strategies among each hyper-parameters.
    • Steps determine the train parameters information content, which means larger steps need larger iterations and larger learning rate.
    • Learning rate should not decay in this program.
    • Larger learning may obtain better performance.

THIS WEEK


Want to do:

  • In my test:
    • Steps must consist among source images pretrain, target images pretrain, transfer pretrain and fine tune.
    • In transfer pretrain learning rate could have a larger number lead iteration count could be small, for last two days experiment, I choose 1e-2 as transfer learning rate.
    • In fine tune step, the learning rate should be as small as possible but not too small, in this experiment I choose 1e-3.
  • So this week I will focus on this experiment.