Live data from Hacker News

Group Normalization

arxiv.org

1–10 of 13 posts

Re: Group Normalization

#7
post #3

Has anyone made or found an implementation yet?

When it comes to using super new research models or methods in deep learning, implementing it yourself instead of looking for other implementations is almost a requirement. In my experience the majority of online "implementations" of research deep learning models or methods have subtle bugs, flaws, or outright implemented something different than the paper they reference. This isn't limited to random github code: for example, I wouldn't trust anything in tensorflow.contrib unless I read the source.

Re: Group Normalization

#8
post #7
post #3

Has anyone made or found an implementation yet?

When it comes to using super new research models or methods in deep learning, implementing it yourself instead of looking for other implementations is almost a requirement. In my experience the majority of online "implementations" of research deep learning models or methods have subtle bugs, flaws, or outright implemented something different than the paper they reference. This isn't limited to random github code: for…

Completely agree. Well, tf.contrib I am usually happy with the docs and a glance through GitHub issues, but, yes, code found elsewhere for very new, or even just recent papers can be really hit or miss, and not always obviously so. There is a lot of great stuff out there, but sometimes even popular papers over a year old can still be a challenge to find good code for. finding 3 separate implementations, all stlighty wrong or unusable is not uncommon.

Re: Group Normalization

#10
post #7
post #3

Has anyone made or found an implementation yet?

When it comes to using super new research models or methods in deep learning, implementing it yourself instead of looking for other implementations is almost a requirement. In my experience the majority of online "implementations" of research deep learning models or methods have subtle bugs, flaws, or outright implemented something different than the paper they reference. This isn't limited to random github code: for…

Having implemented algorithms from research papers I came to the conclusion that the same is true about the papers. It’s unbelievable how bad the quality of the description of algorithms often is.
Post reply on HN