“Asr-language-processing-research-s2s-generation”版本间的差异
来自cslt Wiki
（→Time Table） |
（→Time Table） |
||
| 第10行： | 第10行： | ||
| 2016/11/07-2016/11/13 || | | 2016/11/07-2016/11/13 || | ||
*successfully run the code of "Neural machine translation by jointly learning to align and translate" on gpu | *successfully run the code of "Neural machine translation by jointly learning to align and translate" on gpu | ||
| − | *start | + | *start working on model_step_1: linear trans->cosine->linear trans->softmax; start coding if time permits. |
|| | || | ||
|- | |- | ||
| 第19行： | 第19行： | ||
|- | |- | ||
| 2016/11/21-2016/11/27 || | | 2016/11/21-2016/11/27 || | ||
| − | + | *continue working on model_step_1 | |
| + | *start working on model_step_2: lstm->mn->softmax | ||
|| | || | ||
|- | |- | ||
| − | | 2016/11/28-2016/12/04 || || | + | | 2016/11/28-2016/12/04 || |
| + | *coding & debug & run model_step_2 | ||
| + | *start working on model_step_3: joint training | ||
| + | || | ||
|- | |- | ||
| − | | 2016/12/05-2016/12/11 || || | + | | 2016/12/05-2016/12/11 || |
| + | *coding & debug & run model_step_3 | ||
| + | |||
| + | || | ||
|- | |- | ||
| − | | 2016/12/12-2016/12/18 || || | + | | 2016/12/12-2016/12/18 || |
| + | *find ways to speed up the model if it is slow | ||
| + | || | ||
|- | |- | ||
| − | | 2016/12/19-2016/12/25 || || | + | | 2016/12/19-2016/12/25 || |
| + | *select memory to optimize result | ||
| + | || | ||
|- | |- | ||
| − | | 2016/12/26-2016/12/31 || || | + | | 2016/12/26-2016/12/31 || |
| + | *run final result | ||
| + | *check any possible faults | ||
| + | || | ||
|- | |- | ||
2016年11月8日 (二) 09:52的版本
Main Idea
People
Yang Feng, Andi Zhang
Time Table
| Week | Work Plan | Work Done |
|---|---|---|
| 2016/11/07-2016/11/13 |
|
|
| 2016/11/14-2016/11/20 |
|
|
| 2016/11/21-2016/11/27 |
|
|
| 2016/11/28-2016/12/04 |
|
|
| 2016/12/05-2016/12/11 |
|
|
| 2016/12/12-2016/12/18 |
|
|
| 2016/12/19-2016/12/25 |
|
|
| 2016/12/26-2016/12/31 |
|
