Skip to main content

Deep learning applied to text classification, in PyTorch

Project description

1. The Goal

PyTorch is among the best deep learning frameworks out there. It's relatively easy to use and the coding style is readable and pythonic. Nevertheless, there's still a fair amount of boilerplate code and hard-coded numbers in a typical pytorch project. The goal of this project (a.k.a. inflame) is to abstract away the pieces that remain the same from model to model, so that the same deep learning template, or archetype, can be quickly reapplied to new problems.

2. Quick Start

cd usage
python news_classify
python newsgrp_classify

cd test
python -m unittest discover -v

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

inflame-0.1.2.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

inflame-0.1.2-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file inflame-0.1.2.tar.gz.

File metadata

  • Download URL: inflame-0.1.2.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.6.5

File hashes

Hashes for inflame-0.1.2.tar.gz
Algorithm Hash digest
SHA256 7e53a1b95fd7f9a9b2d2f1f8d5f551948d25c53a54b906cb9add0993171ce94f
MD5 0418c9c0758880de677b15c06d3c3ae7
BLAKE2b-256 aa5625924b70a1a9dd5275f52d79a1bccac0d6e6612678863779256914c17880

See more details on using hashes here.

File details

Details for the file inflame-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: inflame-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 5.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.6.5

File hashes

Hashes for inflame-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 3628622b3ac1cd6d8d13985f9dc5aa117a15b77e8704d3eae77b81a7a5b63452
MD5 e353860741cdcdb7d18c381a0e5869d2
BLAKE2b-256 ee0ebf5de538273caed8fa615101987da2fe6a9bcf363d77d3ae71709438b4bf

See more details on using hashes here.

Supported by

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