Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Receptive Fields #32

Open
hmeine opened this issue Oct 9, 2019 · 1 comment
Open

Receptive Fields #32

hmeine opened this issue Oct 9, 2019 · 1 comment

Comments

@hmeine
Copy link

hmeine commented Oct 9, 2019

First of all, congratulations on this post, or even on the whole of distill.pub. I really think it excels at explaining a lot of things precisely, beautifully, and thoroughly!

In terms of CNN, I like looking at the receptive field a lot. In this post, you mention that the first layers do have a smaller RF. I would love to be able to visualize that, either by cropping the visualizations, or by overlaying a small ROI box. (Personally, I also like to shade everything except the RF of a neuron by blending it to black 80% or so.)

I do understand the limitations of this approach, and the difference between the theoretical and the effective receptive field (which would also be nice to be visualized), but I also do think that a simple RF visualization would be a good addition to this post.

@colah
Copy link
Member

colah commented Oct 17, 2019

Hi Hans! I totally agree that explicitly visualizing the receptive field is a valuable thing one could add. You can see it implicitly in a neuron feature visualization, but you could explore it more explicitly.

That said, I think it's outside the scope of this particular article.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants