Skip to main content

A toolkit for Relation Extraction and more...

Project description



Build Docs

A toolkit for Relation extraction, Event eXtraction (REx) and more...

This project has not been finished yet, so be careful when using it, or wait until the first release comes out.

This project is suffering from the second-system effect. I would like to cut some features to make this going smoothly.

Accelerate seems to be a very sweet wrapper for multi-GPU, TPU training, we highly recommend you to use such frameworks, instead of adding hard codes on your own.

⚙️Installation

Python (>=3.7) and pytorch (>=1.7.1) are preliminaries for REx.

# 1. install from source
$ git clone https://github.com/Spico197/REx.git
$ cd REx
$ pip install -e .

# 2. install from PyPI, recommended
$ pip install pytorch-rex -i https://pypi.org/simple

🚀QuickStart

  • Create a new task: rex new task_name

🤝 Contributing

Contributions are greatly appreciated to make this project better.

Please see Contributing and Code of Conduct for more information.

🔑LICENCE

Distributed under the MIT licence.

See LICENSE for more informatin.

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

pytorch-rex-0.1.8.tar.gz (61.1 kB view details)

Uploaded Source

Built Distribution

pytorch_rex-0.1.8-py3-none-any.whl (81.3 kB view details)

Uploaded Python 3

File details

Details for the file pytorch-rex-0.1.8.tar.gz.

File metadata

  • Download URL: pytorch-rex-0.1.8.tar.gz
  • Upload date:
  • Size: 61.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.9.12

File hashes

Hashes for pytorch-rex-0.1.8.tar.gz
Algorithm Hash digest
SHA256 367bb32332cebf219faf89294e09d205bb785295651b19cdf4c26a07059ddb5d
MD5 21a82480bee89b2f63fb4be328bdfae8
BLAKE2b-256 c706ceccc728dae41773a32b48d4914b1ece6843cd068f1fd776c0d8a0b70e64

See more details on using hashes here.

File details

Details for the file pytorch_rex-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: pytorch_rex-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 81.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.9.12

File hashes

Hashes for pytorch_rex-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 469f7301d4202a9b9107a03b558dbe069c433fa15f6272fd946a931e23c17ce1
MD5 4943e088b30eaf223913a77f0032620e
BLAKE2b-256 5fa1f023b1593fce27d4748a2480f9f483ae1bf5ee5b2fd7cebed8e520159b0d

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