Selozhd/FNet-tensorflow

Tensorflow Implementation of "FNet: Mixing Tokens with Fourier Transforms."

36
/ 100
Emerging

This is a TensorFlow implementation of FNet, a neural network architecture that efficiently processes sequences of data by using Fourier transforms instead of traditional self-attention mechanisms. It's designed to take sequential inputs, like text or time series, and produce embedded representations or predictions, often used for tasks like classification or generation. Data scientists and machine learning engineers working with large sequence datasets can use this for training models more quickly.

No commits in the last 6 months.

Use this if you are a machine learning engineer or data scientist looking for a more computationally efficient way to process long sequences of data for tasks like natural language processing or time series analysis.

Not ideal if you need an out-of-the-box solution for a specific application and are not comfortable with model training and architecture implementation.

natural-language-processing machine-learning-engineering sequence-modeling deep-learning computational-efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

22

Forks

4

Language

Python

License

MIT

Last pushed

May 22, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Selozhd/FNet-tensorflow"

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