Skip to main content

NFNets, PyTorch

Project description

Sharpness Aware Minimization (SAM) in PyTorch

This repository is the generic implementation of sam.pytorch(repository). All credits to @moskomule.

Installation

Latest release: pip install sam-pytorch Latest code: pip install git+https://github.com/tourdeml/sam/

Docs

Visit sam-pytorch.readthedocs.io

Explanation

See the blog post (Tour de ML)

Citation

@ARTICLE{2020arXiv201001412F,
    author = {{Foret}, Pierre and {Kleiner}, Ariel and {Mobahi}, Hossein and {Neyshabur}, Behnam},
    title = "{Sharpness-Aware Minimization for Efficiently Improving Generalization}",
    year = 2020,
    eid = {arXiv:2010.01412},
    eprint = {2010.01412},
}

@software{sampytorch,
    author = {Ryuichiro Hataya},
    titile = {sam.pytorch},
    url    = {https://github.com/moskomule/sam.pytorch},
    year   = {2020}
}

@software{tourdemlsam,
    author = {Vaibhav Balloli},
    titile = "{SAM implementation in PyTorch}",
    url    = {https://github.com/tourdeml/sam},
    year   = {2021}
}

@misc{balloli2021sam:,
  author = {Balloli, Vaibhav},
  title = {Tour de ML: SAM: Sharpness-Aware Maximization},
  url = {https://tourdeml.github.io/blog/posts/2021-02-26-sam-sharpness-aware-maximization/},
  year = {2021}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sam-pytorch-0.0.1.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

sam_pytorch-0.0.1-py3-none-any.whl (4.2 kB view details)

Uploaded Python 3

File details

Details for the file sam-pytorch-0.0.1.tar.gz.

File metadata

  • Download URL: sam-pytorch-0.0.1.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/49.2.1 requests-toolbelt/0.9.1 tqdm/4.58.0 CPython/3.9.1

File hashes

Hashes for sam-pytorch-0.0.1.tar.gz
Algorithm Hash digest
SHA256 d25a9d424e86609c6c6ceb60f205bb9cecdd52554413759a69496b4e9a204a39
MD5 510b7b7c07ac2cb3af2b16920055cd0d
BLAKE2b-256 b75656a6453e06cb21f5043c3bf512925f13e4e403c7489a2238208717eca0bb

See more details on using hashes here.

File details

Details for the file sam_pytorch-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: sam_pytorch-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/49.2.1 requests-toolbelt/0.9.1 tqdm/4.58.0 CPython/3.9.1

File hashes

Hashes for sam_pytorch-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 97dc6db42838400fdb09955b55bce8959b16d74b6111dcd3b6d092bfe0e1657d
MD5 0cfa4676c1d78a7c6c14edfa68efa077
BLAKE2b-256 46427f0f8b61b8f190982b6e6f6ed3ae4c004fee2ed3389569fa6cb7cfe357bb

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page