Skip to main content

"Partial/Fuzzy Conditional random field in PyTorch."

Project description

pytorch-partial-crf

Partial/Fuzzy conditional random field in PyTorch.

How to use

Install

pip install pytorch-partial-crf

Use partial CRF

import torch
from pytorch_partial_crf import PartialCRF

# Create 
num_tags = 6
model = PartialCRF(num_tags)

batch_size, sequence_length = 3, 5
emissions = torch.randn(batch_size, sequence_length, num_tags)

# Set unknown tag to -1
tags = torch.LongTensor([
    [1, 2, 3, 3, 5],
    [-1, 3, 3, 2, -1],
    [-1, 0, -1, -1, 4],
])

# Computing log likelihood
model(emissions, tags)

License

MIT

References

The implementation is based on AllenNLP CRF module and pytorch-crf.

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-partial-crf-0.0.8.tar.gz (5.3 kB view details)

Uploaded Source

Built Distribution

pytorch_partial_crf-0.0.8-py3-none-any.whl (10.4 kB view details)

Uploaded Python 3

File details

Details for the file pytorch-partial-crf-0.0.8.tar.gz.

File metadata

  • Download URL: pytorch-partial-crf-0.0.8.tar.gz
  • Upload date:
  • Size: 5.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.15.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.1

File hashes

Hashes for pytorch-partial-crf-0.0.8.tar.gz
Algorithm Hash digest
SHA256 08b578426267b51b924e7db0399d06db2e6827ad7b18df73d168657cc18542d6
MD5 da3d5365170da86fbd9bf3e9ac22b7d0
BLAKE2b-256 c1b9359a36497daa07c422fc50a02ac3b66c2309d5d1dcf1c6f911f62e10cfaf

See more details on using hashes here.

File details

Details for the file pytorch_partial_crf-0.0.8-py3-none-any.whl.

File metadata

  • Download URL: pytorch_partial_crf-0.0.8-py3-none-any.whl
  • Upload date:
  • Size: 10.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.15.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.1

File hashes

Hashes for pytorch_partial_crf-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 7152e5e70b14b72c515ff0bd501714cbde6ae78ce4b1bc047743075bd7230d63
MD5 36e959729b8ed59fbeb523b40e8b2217
BLAKE2b-256 679826fd01612eade26515161d7017466af52a36d9796e6354f1b81430c1fb6a

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