hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
714 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: 7de69b60b8
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '7de69b60b8'
${ noResults }
xuyige 7de69b60b8 update bert 5 years ago
.github Update PULL_REQUEST_TEMPLATE.md 5 years ago
docs 修改文档的顺序 5 years ago
fastNLP update bert 5 years ago
reproduction 修改为中文注释，增加viterbi解码方法 5 years ago
test - add document 5 years ago
tutorials update advance_tutorial jupyter notebook 5 years ago
.travis.yml * update travis config 5 years ago
LICENSE add LICENSE, setup.py & requirements.txt 6 years ago
MANIFEST.in 1.DataSet.apply()报错时提供错误的index 5 years ago
README.md - update README 5 years ago
codecov.yml add codecov fix 5 years ago
readthedocs.yml update docs 5 years ago
requirements.txt 1. 优化trainer checkcode过程的报错信息 5 years ago
setup.py 修改部分bug；调整callback 5 years ago

README.md

fastNLP

Build Status
codecov
PyPI version
Hex.pm
Documentation Status

FastNLP is a modular Natural Language Processing system based on PyTorch, built for fast development of NLP models.

A deep learning NLP model is the composition of three types of modules:

module type functionality example
encoder encode the input into some abstract representation embedding, RNN, CNN, transformer
aggregator aggregate and reduce information self-attention, max-pooling
decoder decode the representation into the output MLP, CRF

For example:

Requirements

  • Python>=3.6
  • numpy>=1.14.2
  • torch>=0.4.0
  • tensorboardX
  • tqdm>=4.28.1

Resources

Installation

Run the following commands to install fastNLP package.

pip install fastNLP

Models

fastNLP implements different models for variant NLP tasks.
Each model has been trained and tested carefully.

Check out models' performance, usage and source code here.

Project Structure

fastNLP an open-source NLP library
fastNLP.api APIs for end-to-end prediction
fastNLP.core data representation & train/test procedure
fastNLP.models a collection of NLP models
fastNLP.modules a collection of PyTorch sub-models/components/wheels
fastNLP.io readers & savers
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

一款轻量级的自然语言处理（NLP）工具包，目标是减少用户项目中的工程型代码，例如数据处理循环、训练循环、多卡运行等

Python Jupyter Notebook Text CSV Markdown