Skip to content

Latest commit

 

History

History
10 lines (8 loc) · 468 Bytes

README.md

File metadata and controls

10 lines (8 loc) · 468 Bytes
Raw

Fourier Convolutional Neural Network (FCNN)

This repository provides code free to use, for any applications.
In layers.py The implementations of the different layers needed to build and train FCNN has been provided such as :

  • Fourier convolution layers
  • Fourier pooling layer
  • PhaseReLU activation function
  • FFT and IFFT layer

An example of spatial CNN and its FCNN equivalen has also been provided in example_models.py .