https://github.com/speedcell4/torchlatent

High Performance Structured Prediction in PyTorch
https://github.com/speedcell4/torchlatent

conditional-random-fields deep-learning latent-structures matrix-tree-theorem probabilistic-graphical-models pytorch

Last synced: 3 months ago
JSON representation

High Performance Structured Prediction in PyTorch

• Host: GitHub
• URL: https://github.com/speedcell4/torchlatent
• Owner: speedcell4
• License: mit
• Created: 2020-03-01T08:24:23.000Z (about 5 years ago)
• Default Branch: develop
• Last Pushed: 2024-03-14T15:08:52.000Z (about 1 year ago)
• Last Synced: 2024-04-26T07:01:22.909Z (about 1 year ago)
• Topics: conditional-random-fields, deep-learning, latent-structures, matrix-tree-theorem, probabilistic-graphical-models, pytorch
• Language: Python
• Homepage:
• Size: 253 KB
• Stars: 6
• Watchers: 5
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# TorchLatent

![GitHub Workflow Status (with event)](https://img.shields.io/github/actions/workflow/status/speedcell4/torchlatent/unit-tests.yml?cacheSeconds=0)

![PyPI - Version](https://img.shields.io/pypi/v/torchlatent?label=pypi%20version&cacheSeconds=0)

![PyPI - Downloads](https://img.shields.io/pypi/dm/torchlatent?cacheSeconds=0)



## Installation

`python -m pip torchlatent`

## Latent Structures

- [x] Conditional Random Fields (CRF)

- [x] Cocke–Kasami-Younger Algorithm (CKY)

- [ ] Probabilistic Context-free Grammars (CFG)

- [ ] Connectionist Temporal Classification (CTC)

- [ ] Recurrent Neural Network Grammars (RNNG)

- [ ] Non-Projective Dependency Tree (Matrix-tree Theorem)

- [ ] Dependency Model with Valence (DMV)

- [ ] Autoregressive Decoding (Beam Search)