A simple toolbox for meta-learning research based on Pytorch.

Project description

Metallic

Metallic is a clean library for meta-learning research based on PyTorch.

Different from other meta-learning libraries, Metallic aims at providing a lightweight modularized toolbox for setting up meta-learning experiments quickly with the least amount of code.

The library is work in progress.

Installation

git clone https://github.com/Renovamen/metallic.git
cd metallic
python setup.py install

pip install git+https://github.com/Renovamen/metallic.git --upgrade

Documentations

Check the API documentation here: metallic-docs.vercel.app

Acknowledgements

Metallic is highly inspired by the following awesome libraries:

License

Metallic is MIT licensed, see the LICENSE file for more details.

Project details

Release history Release notifications | RSS feed

This version

0.1.0

Mar 5, 2021

Download files

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

Source Distribution

metallic-0.1.0.tar.gz (17.1 kB view details)

Uploaded Mar 5, 2021 Source

Built Distribution

metallic-0.1.0-py3-none-any.whl (27.6 kB view details)

Uploaded Mar 5, 2021 Python 3

File details

Details for the file metallic-0.1.0.tar.gz.

File metadata

Download URL: metallic-0.1.0.tar.gz
Upload date: Mar 5, 2021
Size: 17.1 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.24.0 setuptools/49.6.0.post20200814 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.7.9

File hashes

Hashes for metallic-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`f4cf6562e8fcb4aa138ffd0ea06aaab6c44489cf87a51e6eca85fb92f27f3826`
MD5	`ad5e637ec56eb79fe5e3dfb05b8ee2b7`
BLAKE2b-256	`344d0fe4893b9794f0c4973c10ecdb36059c92c0b6c5860c7baef211e67c93c1`

See more details on using hashes here.

File details

Details for the file metallic-0.1.0-py3-none-any.whl.

File metadata

Download URL: metallic-0.1.0-py3-none-any.whl
Upload date: Mar 5, 2021
Size: 27.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.24.0 setuptools/49.6.0.post20200814 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.7.9

File hashes

Hashes for metallic-0.1.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`8d026f3c316d61a6799abc96f3c6c69afc667c86663de5e7b75f516aff12c25a`
MD5	`5e4c8b5cf4475f1b920a3a15a44375bb`
BLAKE2b-256	`2542a21f5fc5026375c1dcb715e474ee802c72f28a4fee99bab06770931c8c22`