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

Explicit dcgan mnist #373

Merged
merged 7 commits into from
Dec 9, 2022
Merged

Explicit dcgan mnist #373

merged 7 commits into from
Dec 9, 2022

Conversation

mcabbott
Copy link
Member

@mcabbott mcabbott commented Dec 8, 2022

Last I upgraded a few models to use explicit-mode gradients, Flux 0.13.9.

They do run, but I did not check with a GPU, nor run them for the full number of epochs.

In several of these, I also

  • Removed Parameters.jl, this seems weird as it's built-in, and the whole make-a-struct-for-parameters style here seems over-engineered already.
  • Removed elaborate code for defining device = gpu etc. Isn't the point of gpu that it warns you then does nothing, if used without a GPU?

(Separate commits, to be easy to remove if people have strong feelings.)

Co-authored-by: Michael Abbott <32575566+mcabbott@users.noreply.github.com>
@mcabbott mcabbott merged commit 0982bae into master Dec 9, 2022
@mcabbott mcabbott deleted the explicit_dcgan_mnist branch December 9, 2022 18:29
@mcabbott mcabbott added the update making a model work with latest Flux, etc label Dec 11, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
update making a model work with latest Flux, etc
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants