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.

Sign up for GitHub

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

Jump to bottom

Use PyTorch as the reference deep learning framework/architecture for future projects #211

Closed
antoinecarme opened this issue Aug 30, 2022 · 2 comments
Closed

Use PyTorch as the reference deep learning framework/architecture for future projects #211

antoinecarme opened this issue Aug 30, 2022 · 2 comments
Assignees
@antoinecarme
Labels
class:enhancement priority:high topic:modeling_quality topic:neural_net

Comments

@antoinecarme
Copy link
Owner

PyAF will use PyTorch as its deep learning architecture for future projects. A few reasons for this :

  1. Pytorch is fully open source. Green (Ensure that PyAF is and remains Green #176 )
  2. PyTorch internal/technical choices are very sane. It works even in very hash environments : SPARC64 architecture.
  3. SPARC64 architecture : abandoned years ago, no commercial support, very strong technically ( manycore, > 128 threads), with approximate OS (Debian rocks here ;), was able to build a set of packages for PyTorch from scratch : https://github.com/antoinecarme/sparc-t3-data/tree/master/debian-sparc64/packages
  4. PyAF runs OK with PyTorch on SPARC64 and uses all the 128 threads for some complex hierarchical forecasting models.
@antoinecarme
Copy link
Owner Author

Get rid of Keras and tensorflow. And now that we have pytorch working (#199 ), no need for scikeras in a pyaf context neither.

Less is better. Minimal is beautiful.

DeprecationWarning: KerasRegressor is deprecated, use Sci-Keras (https://github.com/adriangb/scikeras) instead. See https://www.adriangb.com/scikeras/stable/migration.html for help migrating.

@antoinecarme antoinecarme mentioned this issue Aug 30, 2022
Closed
antoinecarme added a commit that referenced this issue Dec 7, 2022
@antoinecarme
Use PyTorch as the reference deep learning architecture for future p…
b643c84 
…rojects #211
@antoinecarme antoinecarme self-assigned this Dec 7, 2022
@antoinecarme antoinecarme mentioned this issue Jan 14, 2023
Open
antoinecarme added a commit that referenced this issue Feb 4, 2023
@antoinecarme
Use PyTorch as the reference deep learning architecture for future pr…
eba4180 
…ojects #211. Removed some old dependencies.
@antoinecarme antoinecarme changed the title Use PyTorch as the reference deep learning architecture for future projects Use PyTorch as the reference deep learning framework/architecture for future projects Feb 9, 2023
@antoinecarme antoinecarme mentioned this issue Mar 9, 2023
Closed
@antoinecarme
Copy link
Owner Author

Closing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@antoinecarme antoinecarme

Labels
class:enhancement priority:high topic:modeling_quality topic:neural_net
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@antoinecarme