Skip to main content

Layer AI SDK

Project description


Layer

License Documentation Build PyPI Contributor Covenant

Layer - Metadata Store for Production ML

Layer helps you build, train and track all your machine learning project metadata including ML models and datasets with semantic versioning, extensive artifact logging and dynamic reporting with local↔cloud training

Start for Free now!

Getting Started

Install Layer:

pip install layer --upgrade

Login to your free account and initialize your project:

import layer
layer.login()
layer.init("my-first-project")

Decorate your training function to register your model to Layer:

from layer.decorators import model

@model("my-model")
def train():
    from sklearn import datasets
    from sklearn.svm import SVC
    iris = datasets.load_iris()
    clf = SVC()
    clf.fit(iris.data, iris.target)
    return clf

train()

Now you can fetch your model from Layer:

import layer

clf = layer.get_model("my-model:1.1").get_train()
clf

# > SVC()

🚀 Try in Google Colab now!

Reporting bugs

You have a bug, a request or a feature? Let us know on Slack or open an issue

Contributing code

Do you want to help us build the best metadata store? Check out the Contributing Guide

Learn more

Project details


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

layer-0.10.2390270851.tar.gz (95.6 kB view details)

Uploaded Source

Built Distribution

layer-0.10.2390270851-py3-none-any.whl (129.2 kB view details)

Uploaded Python 3

File details

Details for the file layer-0.10.2390270851.tar.gz.

File metadata

  • Download URL: layer-0.10.2390270851.tar.gz
  • Upload date:
  • Size: 95.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.13 CPython/3.8.12 Linux/5.4.0-1078-azure

File hashes

Hashes for layer-0.10.2390270851.tar.gz
Algorithm Hash digest
SHA256 fcf6ce177e515343987af7fb6a6f55f1ea877df6ba80bc31f2d4eaaf8434ece9
MD5 ed291801a540f541f02b5f063c770f78
BLAKE2b-256 1b122dd588fb07ac283c1b276f3af3e8ddb941f49c26ead6d4c594215e7c3ec1

See more details on using hashes here.

File details

Details for the file layer-0.10.2390270851-py3-none-any.whl.

File metadata

  • Download URL: layer-0.10.2390270851-py3-none-any.whl
  • Upload date:
  • Size: 129.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.13 CPython/3.8.12 Linux/5.4.0-1078-azure

File hashes

Hashes for layer-0.10.2390270851-py3-none-any.whl
Algorithm Hash digest
SHA256 b0775fdc85a2b123d7563603fb3d17449ea35f32107a2c0c9aca97269416bcf6
MD5 99a647eeddc819562756474b746909b5
BLAKE2b-256 c224211f2c19bfeb65522fe5bcaf21af3067857c64f3af4bef33270ecda20ca0

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