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

Documentation for writing your own custom loss function #106

Closed
JamieMair opened this issue Sep 16, 2022 · 1 comment
Closed

Documentation for writing your own custom loss function #106

JamieMair opened this issue Sep 16, 2022 · 1 comment

Comments

@JamieMair
Copy link
Contributor

JamieMair commented Sep 16, 2022

Is there any documentation for implementing a custom loss function, e.g. something similar to LogitCrossEntropyLoss?

I have been looking here - https://github.com/PumasAI/SimpleChains.jl/blob/a735c44c976aa699b6263629b4c21c227504ad08/src/loss.jl and some code that looks similar to what I need to write, such as the chain_valgrad! function, but I am lost on what the variable names represent. Specifically, what are pu,p, arg, m etc? Any guidance would be appreciated

@DoktorMike
Copy link

Shouldn't this issue be closed as there's already a MR that fixes it?

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

3 participants