Skip to main content

minGRU

Project description

minGRU

Implementation of the proposed minGRU in Pytorch, only the log-space numerically stable version.

Install

$ pip install minGRU-pytorch

Usage

import torch
from minGRU_pytorch import minGRU

min_gru = minGRU(512)

x = torch.randn(2, 1024, 512)

out = min_gru(x)

assert x.shape == out.shape

Test

enwik8

$ python train.py

Citations

@inproceedings{Feng2024WereRA,
    title   = {Were RNNs All We Needed?},
    author  = {Leo Feng and Frederick Tung and Mohamed Osama Ahmed and Yoshua Bengio and Hossein Hajimirsadegh},
    year    = {2024},
    url     = {https://api.semanticscholar.org/CorpusID:273025630}
}

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

mingru_pytorch-0.0.10.tar.gz (36.6 MB view details)

Uploaded Source

Built Distribution

mingru_pytorch-0.0.10-py3-none-any.whl (5.5 kB view details)

Uploaded Python 3

File details

Details for the file mingru_pytorch-0.0.10.tar.gz.

File metadata

  • Download URL: mingru_pytorch-0.0.10.tar.gz
  • Upload date:
  • Size: 36.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for mingru_pytorch-0.0.10.tar.gz
Algorithm Hash digest
SHA256 8c25b2ae8155e51700098edc57092550e1e9d67b47232ccb1683d8b7882fda4b
MD5 b357bb5afded9f1c73f950e941dd6e94
BLAKE2b-256 8fdd0a83da31a3497d0915f6a5033ddf81f2a86b3e47268a3e03dae22b4e08cf

See more details on using hashes here.

File details

Details for the file mingru_pytorch-0.0.10-py3-none-any.whl.

File metadata

File hashes

Hashes for mingru_pytorch-0.0.10-py3-none-any.whl
Algorithm Hash digest
SHA256 d48e1d7ffb0ae123ba8a12899bf1b2727546bb6ff54d08b8b36ef6ed34d9e273
MD5 c9d83999434ea95a461f9530eb9d7af5
BLAKE2b-256 81aede84cf920c80770041918eb761993200291ad5418a290cbdb876c8b16c5a

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