Anirudh Goyal

Thanks @ziyuwwang for letting me know. It's possible there's some discrepancy somewhere. I'll take a look in next few days. (I've my PhD qualifier talk in coming week). If you...

Hello @ziyuwwang, This is the configuration (copied from my code, used in the paper) which gave approximately the same result. Learning rate: 0.001 600, 6RIMs, top_k = 4, dropout =...

Also, note we did use the above configuration for most of our experiments. Only thing to be careful of 1. Usage of dropout. For bouncing balls, using dropout in the...

>It's very nice of you to give so many useful suggestions @anirudh9119 ! But still I cannot get a result close to that of the original paper after running the...

@ziyuwwang I think I suggested above to use. 600, 6RIMs, top_k = 4.

Thanks @antoniogois. I'll see what's making the difference.

May be a moot point but still, what pytorch version are you using @antoniogois ?

@antoniogois @ziyuwwang I'm investigating. I'm not sure, whats going on wrong as of now. I ran again with the https://drive.google.com/file/d/1KKz3YEyZJ4-2XY40d7akrrrBynG9elVT/view?usp=sharing. I got same results. (It's the official code, I used,...

Sorry. Changed it. the code in zip, and the code here is same. One of my colleagues was also not able to reproduce the results, so I'm looking at it....

@antoniogois @ziyuwwang With everything installed from scratch, I was also able to "reproduce" the issue. (i.e results dont match). Training logs for the setting where I was able to reproduce...