All Projects → kmkurn → Pytorch Crf

kmkurn / Pytorch Crf

Licence: mit
(Linear-chain) Conditional random field in PyTorch.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pytorch Crf

Ofxdarknet
darknet neural network addon for openFrameworks
Stars: ✭ 493 (-22.12%)
Mutual labels:  neural-networks
Keras Js
Run Keras models in the browser, with GPU support using WebGL
Stars: ✭ 4,855 (+666.98%)
Mutual labels:  neural-networks
Awesome Bert Nlp
A curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.
Stars: ✭ 567 (-10.43%)
Mutual labels:  neural-networks
Geomstats
Computations and statistics on manifolds with geometric structures.
Stars: ✭ 498 (-21.33%)
Mutual labels:  neural-networks
Speech Denoising Wavenet
A neural network for end-to-end speech denoising
Stars: ✭ 516 (-18.48%)
Mutual labels:  neural-networks
Layer
Neural network inference the Unix way
Stars: ✭ 539 (-14.85%)
Mutual labels:  neural-networks
Deep Learning Specialization Coursera
Deep Learning Specialization by Andrew Ng on Coursera.
Stars: ✭ 483 (-23.7%)
Mutual labels:  neural-networks
Deep Learning For Hackers
Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)
Stars: ✭ 586 (-7.42%)
Mutual labels:  neural-networks
Sense
Enhance your application with the ability to see and interact with humans using any RGB camera.
Stars: ✭ 522 (-17.54%)
Mutual labels:  neural-networks
Flashtorch
Visualization toolkit for neural networks in PyTorch! Demo -->
Stars: ✭ 561 (-11.37%)
Mutual labels:  neural-networks
Edward
A probabilistic programming language in TensorFlow. Deep generative models, variational inference.
Stars: ✭ 4,674 (+638.39%)
Mutual labels:  neural-networks
Machine Learning Articles
Monthly Series - Top 10 Machine Learning Articles
Stars: ✭ 516 (-18.48%)
Mutual labels:  neural-networks
Tensorflow Value Iteration Networks
TensorFlow implementation of the Value Iteration Networks (NIPS '16) paper
Stars: ✭ 549 (-13.27%)
Mutual labels:  neural-networks
Chemprop
Message Passing Neural Networks for Molecule Property Prediction
Stars: ✭ 501 (-20.85%)
Mutual labels:  neural-networks
Tez
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
Stars: ✭ 580 (-8.37%)
Mutual labels:  neural-networks
Learn Data Science For Free
This repositary is a combination of different resources lying scattered all over the internet. The reason for making such an repositary is to combine all the valuable resources in a sequential manner, so that it helps every beginners who are in a search of free and structured learning resource for Data Science. For Constant Updates Follow me in …
Stars: ✭ 4,757 (+651.5%)
Mutual labels:  neural-networks
Graph nets
Build Graph Nets in Tensorflow
Stars: ✭ 5,051 (+697.95%)
Mutual labels:  neural-networks
Nengo
A Python library for creating and simulating large-scale brain models
Stars: ✭ 615 (-2.84%)
Mutual labels:  neural-networks
Efficient Segmentation Networks
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
Stars: ✭ 579 (-8.53%)
Mutual labels:  neural-networks
Keras Rl
Deep Reinforcement Learning for Keras.
Stars: ✭ 5,166 (+716.11%)
Mutual labels:  neural-networks

pytorch-crf

Conditional random field in PyTorch <http://pytorch.org/>_.

.. image:: https://img.shields.io/pypi/pyversions/pytorch-crf.svg?style=flat :target: https://img.shields.io/pypi/pyversions/pytorch-crf.svg?style=flat :alt: Python versions

.. image:: https://img.shields.io/pypi/v/pytorch-crf.svg?style=flat :target: https://pypi.org/project/pytorch-crf :alt: PyPI project

.. image:: https://img.shields.io/travis/kmkurn/pytorch-crf.svg?style=flat :target: https://travis-ci.org/kmkurn/pytorch-crf :alt: Build status

.. image:: https://img.shields.io/readthedocs/pytorch-crf.svg?style=flat :target: https://pytorch-crf.readthedocs.io :alt: Documentation status

.. image:: https://img.shields.io/coveralls/github/kmkurn/pytorch-crf.svg?style=flat :target: https://coveralls.io/github/kmkurn/pytorch-crf :alt: Code coverage

.. image:: https://img.shields.io/pypi/l/pytorch-crf.svg?style=flat :target: https://choosealicense.com/licenses/mit/ :alt: License

.. image:: https://cdn.rawgit.com/syl20bnr/spacemacs/442d025779da2f62fc86c2082703697714db6514/assets/spacemacs-badge.svg :target: http://spacemacs.org :alt: Built with Spacemacs

This package provides an implementation of linear-chain conditional random field <https://en.wikipedia.org/wiki/Conditional_random_field>_ (CRF) in PyTorch. This implementation borrows mostly from AllenNLP CRF module <https://github.com/allenai/allennlp/blob/master/allennlp/modules/conditional_ra ndom_field.py>_ with some modifications.

Documentation

https://pytorch-crf.readthedocs.io/

License

MIT

Contributing

Contributions are welcome! Please follow these instructions to install dependencies and running the tests and linter.

Installing dependencies

Make sure you setup a virtual environment with Python. Then, install all the dependencies in requirements.txt file and install this package in development mode.

::

pip install -r requirements.txt
pip install -e .

Setup pre-commit hook

Simply run::

ln -s ../../pre-commit.sh .git/hooks/pre-commit

Running tests

Run pytest in the project root directory.

Running linter

Run flake8 in the project root directory. This will also run mypy, thanks to flake8-mypy package.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].