Skip to content
New issue

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

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

Already on GitHub? # to your account

add default value to rms_decay and fix documentation #4379

Merged
merged 2 commits into from
Aug 11, 2016

Conversation

alicanb
Copy link
Contributor

@alicanb alicanb commented Jun 28, 2016

fixes #3472 and fixes #3930

@alicanb
Copy link
Contributor Author

alicanb commented Aug 11, 2016

@jeffdonahue would you mind taking a look? By 'fix' documentation I really mean 'FIX' documentation. Current RMSprop in docs is completely wrong and misleading. People are writing redundant issues and PRs regarding this.

@lukeyeager
Copy link
Contributor

So I should close #4567, then?

@alicanb
Copy link
Contributor Author

alicanb commented Aug 11, 2016

@lukeyeager Yep

@jeffdonahue
Copy link
Contributor

Thanks @alicanb, this seems right to me. (It's definitely bad that this defaults to 0 now, didn't realize that...)

@jeffdonahue jeffdonahue merged commit d91572d into BVLC:master Aug 11, 2016
fxbit pushed a commit to Yodigram/caffe that referenced this pull request Sep 1, 2016
add default value to rms_decay and fix documentation
# for free to join this conversation on GitHub. Already have an account? # to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

RMSProp solver is different from the one described on the tutorial page? rms_decay's default value not set
4 participants