Skip to main content

High level interface for text applications using PyTroch RNN's.

Project description

GeNN

GitHub license

GeNN (generative neural networks) is a high-level interface for text applications using PyTorch RNN's.

Features

  1. Preprocessing:
    • Parsing txt, json, and csv files.
    • NLTK, regex and spacy tokenization support.
    • GloVe and fastText pretrained embeddings, with the ability to fine-tune for your data.
  2. Architectures and customization:
    • GPT-2 with small, medium, and large variants.
    • LSTM and GRU, with variable size.
    • Variable number of layers and batches.
    • Dropout.
  3. Text generation:
    • Random seed sampling from the n first tokens in all instances, or the most frequent token.
    • Top-K sampling for next token prediction with variable K.
    • Nucleus sampling for next token prediction with variable probability threshold.

Getting started

How to install

pip install genn

Prerequisites

  • PyTorch 1.4.0
pip install torch==1.4.0
  • Pytorch Transformers
pip install pytorch_transformers
  • NumPy
pip install numpy
  • fastText
pip install fasttext

Use the package manager pip to install genn.

Usage

from genn import Preprocessing, LSTMGenerator, GPT2
#LSTM example
ds = Preprocessing("data.txt")
gen = LSTMGenerator(ds, nLayers = 2,
                        batchSize = 16,
                        embSize = 64,
                        lstmSize = 16,
                        epochs = 20)

#Train the model
gen.run()

# Generate 5 new documents
print(gen.generate_document(5))

#GPT-2 example
gen = GPT2("data.txt",
 	    taskToken = "Movie:",
	    epochs = 7,
	    variant = "medium")
#Train the model
gen.run()

#Generate 10 new documents
print(gen.generate_document(10))

For more examples on how to use Preprocessing, please refer to this file.

For more examples on how to use LSTMGenerator and GRUGenerator, please refer to this file.

For more examples on how to use GPT2, please refer to this file

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

Distributed under the MIT License. See LICENSE for more information.

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

abdoTheBest-0.7.8.tar.gz (11.7 kB view details)

Uploaded Source

Built Distribution

abdoTheBest-0.7.8-py3-none-any.whl (15.1 kB view details)

Uploaded Python 3

File details

Details for the file abdoTheBest-0.7.8.tar.gz.

File metadata

  • Download URL: abdoTheBest-0.7.8.tar.gz
  • Upload date:
  • Size: 11.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.23.0 setuptools/47.1.1 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for abdoTheBest-0.7.8.tar.gz
Algorithm Hash digest
SHA256 6de8f8f965e9a674430067166bd031a39e286cecd0465926cbbd53c4d82486e5
MD5 d4fb7f5ced8b31fc77ec5acf4f82ae22
BLAKE2b-256 6c0e355c0afa4b65ee9f1cd7f08863e99ca9c18ba135634243a9b1d9f106335f

See more details on using hashes here.

File details

Details for the file abdoTheBest-0.7.8-py3-none-any.whl.

File metadata

  • Download URL: abdoTheBest-0.7.8-py3-none-any.whl
  • Upload date:
  • Size: 15.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.23.0 setuptools/47.1.1 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for abdoTheBest-0.7.8-py3-none-any.whl
Algorithm Hash digest
SHA256 56649481e1443bba73ce2fe6dd8634bef03dd0fde893ae1fa41a0362dc88cb51
MD5 6783ee8386cdfe265eb40adcb33e68c6
BLAKE2b-256 6d1f054a366d863cdab95218fe160382d222f4c56fa47448466a851bbc9b98ad

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