Selozhd/FNet-tensorflow
Tensorflow Implementation of "FNet: Mixing Tokens with Fourier Transforms."
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.
Stars
22
Forks
4
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action