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

Conditional Random Fields #162

Merged
merged 40 commits into from
Jul 29, 2019
Merged

Conditional Random Fields #162

merged 40 commits into from
Jul 29, 2019

Conversation

Ayushk4
Copy link
Member

@Ayushk4 Ayushk4 commented Jun 14, 2019

  • Viterbi Decode
  • Supports for training with Flux Layers
  • Documentation
  • Tests
  • Extended example over the Flux layers

@aviks aviks requested a review from MikeInnes June 15, 2019 22:33
@MikeInnes
Copy link
Contributor

Seems fine to me code style wise; @aviks don't know if you want any deeper look over this, but it's not a model I'm really familiar with.

Could probably use some tests / a usage demo but you have that listed. If this is something that's designed to be trained by users, rather than classifying things out of the box, maybe there's a case for just having it in Flux itself?

You might want to look at Flux.@treelike so that this model can be moved the the GPU and such.

@Ayushk4 Ayushk4 changed the title [WIP]: Conditional Random Fields Conditional Random Fields Jul 22, 2019
@Ayushk4
Copy link
Member Author

Ayushk4 commented Jul 28, 2019

@aviks Please review this PR.

@aviks
Copy link
Member

aviks commented Jul 29, 2019

I'm merging this here for now. It may be worth moving to Flux, but I don't want to make that a blocker for further work. Ayush, you may want to make a PR to Flux at some point with this model, but it's not urgent.

@aviks aviks merged commit 8b46a70 into JuliaText:master Jul 29, 2019
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

Successfully merging this pull request may close these issues.

3 participants