rishikksh20/FNet-pytorch

Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

44
/ 100
Emerging

FNet is a specialized tool for machine learning practitioners working with sequence data, such as text or time series. It processes this data using an efficient method based on Fourier Transforms to prepare it for tasks like classification or prediction. This project is ideal for researchers and engineers who build and experiment with neural network models.

262 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking for an alternative, computationally efficient way to process sequence data within your deep learning models.

Not ideal if you are looking for a plug-and-play solution for a specific data analysis problem, as this requires familiarity with neural network architectures and PyTorch.

deep-learning-research natural-language-processing sequence-modeling neural-network-architecture computational-efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

262

Forks

37

Language

Python

License

MIT

Last pushed

May 18, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/rishikksh20/FNet-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.