Skip to content
This repository has been archived by the owner on Nov 1, 2024. It is now read-only.

Sweep code for studying model population stats (1 of 2) #143

Closed
wants to merge 1 commit into from

Conversation

rajprateek
Copy link
Member

This is a major update and introduces powerful new functionality to pycls.

The pycls codebase now provides powerful support for studying design spaces and more generally population statistics of models as introduced in On Network Design Spaces for Visual Recognition and Designing Network Design Spaces. This idea is that instead of planning a single pycls job (e.g., testing a specific model configuration), one can study the behavior of an entire population of models. This allows for quite powerful and succinct experimental design, and elevates the study of individual model behavior to the study of the behavior of model populations. Please see SWEEP_INFO for details.

This is commit 1 of 2 for the sweep code. It is focused on the sweep config, setting up the sweep, and launching it.

Co-authored-by: Raj Prateek Kosaraju rajprateek@users.noreply.github.com
Co-authored-by: Piotr Dollar pdollar@gmail.com

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 20, 2021
@facebook-github-bot
Copy link

@rajprateek has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link

@rajprateek has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

This is a *major update* and introduces powerful new functionality to pycls.

The pycls codebase now provides powerful support for studying *design spaces* and more generally *population statistics* of models as introduced in [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214) and [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678). This idea is that instead of planning a single pycls job (e.g., testing a specific model configuration), one can study the behavior of an entire population of models. This allows for quite powerful and succinct experimental design, and elevates the study of individual model behavior to the study of the behavior of model populations. Please see [`SWEEP_INFO`](docs/SWEEP_INFO.md) for details.

This is commit 1 of 2 for the sweep code. It is focused on the sweep config, setting up the sweep, and launching it.

Co-authored-by: Raj Prateek Kosaraju <rajprateek@users.noreply.github.com>
Co-authored-by: Piotr Dollar <699682+pdollar@users.noreply.github.com>
@rajprateek rajprateek changed the title Sweep code for studying model population stats (commit 1 of 2) Sweep code for studying model population stats (1 of 2) May 20, 2021
@facebook-github-bot
Copy link

@rajprateek has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link

@rajprateek merged this pull request in bd65938.

@pdollar pdollar deleted the sweep-commit1 branch May 20, 2021 23:13
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants