Skip to main content

A deep learning package for self-supervised learning

Project description

Lightly

Lightly is a PIP package for self-supervised learning.

We, at Lightly, are passionate engineers who want to make deep learning more efficient. We want to help popularize the use of self-supervised methods to understand and filter raw image data. Our solution can be applied before any data annotation step and the learned representations can be used to analyze and visualize datasets as well as for selecting a core set of samples.

If you are curious to learn more about our work - check out Lightly!

Installation

pip install lightly

Links

Release history Release notifications | RSS feed

Download files

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

Source Distribution

lightly-1.2.3.tar.gz (151.7 kB view details)

Uploaded Source

Built Distribution

lightly-1.2.3-py3-none-any.whl (323.2 kB view details)

Uploaded Python 3

File details

Details for the file lightly-1.2.3.tar.gz.

File metadata

  • Download URL: lightly-1.2.3.tar.gz
  • Upload date:
  • Size: 151.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.9.7

File hashes

Hashes for lightly-1.2.3.tar.gz
Algorithm Hash digest
SHA256 512cd12d06a79826f895584a5e46c797c19010b625465ab632d25d4ee2a07966
MD5 db03e12e964823bd1a4bd530d2b8d487
BLAKE2b-256 6b5857bbc27f04c7ba2bfffb040c45a3d40cb7874bb1efb450ef7cef2d3582a0

See more details on using hashes here.

File details

Details for the file lightly-1.2.3-py3-none-any.whl.

File metadata

  • Download URL: lightly-1.2.3-py3-none-any.whl
  • Upload date:
  • Size: 323.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.9.7

File hashes

Hashes for lightly-1.2.3-py3-none-any.whl
Algorithm Hash digest
SHA256 e033f34147d33446b15a108890c892a6d95c685aaea2d2b3fda748a29ff3a4aa
MD5 3db4b724038b6c064b2997ad7958ef18
BLAKE2b-256 92a9e1e3ddc11c06be0fc82fb569b84daa7490c0b52d4d499b3ff89109a50cf0

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