upccpu

> @fawazsammani i feel like this level of difference should not be fundamentally different. You can try. (I tried the instance norm too, the same here) Hi, ruotianluo. In my...

Yeah. I agree with you. But, i only obtained 1.150(less than 1.166) with the transfomer_step setting (in /Config/transformer/transformer_step). And, i can obtain 1.182 when using my own algorithm(same configuration). However,...

> @upccpu it seems correct. For transformer its usually 12 points from XE checkpoint under SCST To be honest, the imporvements of SCST depend on the algorithmic innovation, rather than...

@fawazsammani It also confuses me. Maybe, they use some tricks. Thanks for your advice.

Hi, @fawazsammani . About the instance normalization. In my opinion, it is not necessary to consider the mask. If there is a feature with such demensions[B, C, W, H], Instance...

@fawazsammani Thanks ~.~. I am conducting the experiments based on your masked instance norm. Thanks for your reply again. I help me a lot.

@ruotianluo I have tested the performance many times based on AOA's original code. However, i found that i couldn't get close to the cider score, which they mentioned in the...

@ruotianluo 谢谢您的回复。我的英语水平不好，直接上中文了。我用了他给的源代码（保持论文相同地参数），也测试了使用SCST后的效果，但结果并没有他论文里的那么好（少1.5-2的百分点）。我在github上给作者留了言，他没有回复我。因为您在这方面是权威，所以我就想问一下您是否能给出一些可能的原因。万分感谢您的这个项目，这几年来它给了我很大的帮助。

@ruotianluo 我跑了4次他的源代码，最高就在128.3这样(beamsize设置的3).我现在基于他的源代码加入了一些我的东西，然后能得到129.6的结果。但是还是没有他论文结果好。所以我也没办法下手写这篇文章，感觉这样下笔很不严谨。

@ruotianluo 他用文章里的比github上的结果高不少，能到129.8。他解释给别人的原因是随机初始化导致的，但我感觉不会差那么多。