Zhiyuan Tang 2015-09-07 - 版本历史

2015年9月7日 (一) 21:16 Tangzy

2015-09-07T21:16:59Z

2015年9月7日 (一) 20:55 Tangzy

2015-09-07T20:55:05Z

Tangzy：以“ Last week: 1. got the result of re-tuned bidirectional net on WSJ with dark knowledge, which is the best; 2. got more results of end-to-end ASR with B-LSTM on bi...”为内容创建页面

2015-09-07T19:44:15Z

以“ Last week: 1. got the result of re-tuned bidirectional net on WSJ with dark knowledge, which is the best; 2. got more results of end-to-end ASR with B-LSTM on bi...”为内容创建页面

新页面

Last week:

1. got the result of re-tuned bidirectional net on WSJ with dark knowledge, which is the best;

2. got more results of end-to-end ASR with B-LSTM on bigger data (1000+ hours) for basic comparison;

3. with Xuewei, reproduced the process of reorganizing a picture with the style of another specific picture

on a laptop, while subject to the limit of the laptop's memory, only very small pictures,

then we moved the system to the grid, still some problems.

This week:

1. rebuild the neural art style transfer system on the grid totally, and do some further modification;

2. other regular experiments.

@@ 第8行： / 第8行： @@
 . with Xuewei, reproduced the process of reorganizing a picture with the style of another specific picture
-on a laptop, while subject to the limit of the laptop's memory, only very small pictures,
+on a laptop, while subject to the laptop's memory, limited to inception net with sgd optimizer
 then we moved the system to the grid, still the problem, while we want to solve it via software rather than hardware.

←上一版本		2015年9月7日 (一) 20:55的版本
第10行：		第10行：
	on a laptop, while subject to the limit of the laptop's memory, only very small pictures,		on a laptop, while subject to the limit of the laptop's memory, only very small pictures,

−	then we moved the system to the grid, still ~~some problems~~.	+	then we moved the system to the grid, still the problem, while we want to solve it via software rather than hardware.