Skip to main content

None

Project description

pytorch-fast-elmo

https://img.shields.io/pypi/v/pytorch_fast_elmo.svg https://img.shields.io/travis/cnt-dev/pytorch-fast-elmo.svg https://img.shields.io/badge/License-MIT-yellow.svg

Introduction

A fast ELMo implementation with features:

  • Lower execution overhead. The core components are reimplemented in Libtorch in order to reduce the Python execution overhead (45% speedup).

  • A more flexible design. By redesigning the workflow, the user could extend or change the ELMo behavior easily.

Benchmark

Hardware:

  • CPU: i7-7800X

  • GPU: 1080Ti

Options:

  • Batch size: 32

  • Warm up iterations: 20

  • Test iterations: 1000

  • Word length: [1, 20]

  • Sentence length: [1, 30]

  • Random seed: 10000

Item

Mean Of Durations (ms)

cumtime(synchronize)%

Fast ELMo (CUDA, no synchronize)

31

N/A

AllenNLP ELMo (CUDA, no synchronize)

56

N/A

Fast ELMo (CUDA, synchronize)

47

26.13%

AllenNLP ELMo (CUDA, synchronize)

57

0.02%

Fast ELMo (CPU)

1277

N/A

AllenNLP ELMo (CPU)

1453

N/A

Usage

Please install torch==1.0.0 first. Then, simply run this command to install.

pip install pytorch-fast-elmo

FastElmo should have the same behavior as AllenNLP’s ELMo.

from pytorch_fast_elmo import FastElmo, batch_to_char_ids

options_file = '/path/to/elmo_2x4096_512_2048cnn_2xhighway_options.json'
weight_file = '/path/to/elmo_2x4096_512_2048cnn_2xhighway_weights.hdf5'

elmo = FastElmo(options_file, weight_file)

sentences = [['First', 'sentence', '.'], ['Another', '.']]
character_ids = batch_to_ids(sentences)

embeddings = elmo(character_ids)

Use FastElmoWordEmbedding if you have disabled char_cnn in bilm-tf, or have exported the Char CNN representation to a weight file.

from pytorch_fast_elmo import FastElmoWordEmbedding, load_and_build_vocab2id, batch_to_word_ids

options_file = '/path/to/elmo_2x4096_512_2048cnn_2xhighway_options.json'
weight_file = '/path/to/elmo_2x4096_512_2048cnn_2xhighway_weights.hdf5'

vocab_file = '/path/to/vocab.txt'
embedding_file = '/path/to/cached_elmo_embedding.hdf5'

elmo = FastElmoWordEmbedding(
        options_file,
        weight_file,
        # Could be omitted if the embedding weight is in `weight_file`.
        word_embedding_weight_file=embedding_file,
)
vocab2id = load_and_build_vocab2id(vocab_file)

sentences = [['First', 'sentence', '.'], ['Another', '.']]
word_ids = batch_to_word_ids(sentences, vocab2id)

embeddings = elmo(word_ids)

CLI commands:

# Cache the Char CNN representation.
fast-elmo cache-char-cnn ./vocab.txt ./options.json ./lm_weights.hdf5 ./lm_embd.hdf5

# Export word embedding.
fast-elmo export-word-embd ./vocab.txt ./no-char-cnn.hdf5 ./embd.txt

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

History

0.1.0 (2019-01-02)

  • First release on PyPI.

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_fast_elmo-0.6.9.tar.gz (429.8 kB view details)

Uploaded Source

File details

Details for the file pytorch_fast_elmo-0.6.9.tar.gz.

File metadata

  • Download URL: pytorch_fast_elmo-0.6.9.tar.gz
  • Upload date:
  • Size: 429.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.7

File hashes

Hashes for pytorch_fast_elmo-0.6.9.tar.gz
Algorithm Hash digest
SHA256 981b0533d3f5ea9e863d59bcdf82fc9592b5f5c48cf7fcf61a7df32bc0367841
MD5 edc80c1c67e39d360f6393b58b117994
BLAKE2b-256 34fa85ed4e9b5bce082267d95620a48966cb08ed1bbc40a8c4d12fb266788e48

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