项目作者: zaccharieramzi

项目描述 :
A package to easily install tensorflow utils for complex-valued tensors and neural networks
高级语言: Python
项目地址: git://github.com/zaccharieramzi/tf-complex.git
创建时间: 2020-07-28T09:51:05Z
项目社区:https://github.com/zaccharieramzi/tf-complex

开源协议:MIT License

下载


tf-complex

Build Status

This package was inspired by the work of Elizabeth Cole et al.: Image Reconstruction using an Unrolled DL Architecture including Complex-Valued Convolution and Activation Functions.
Please cite their work appropriately if you use this package.
The code for their work is available here.

Installation

You can install tf-complex using pypi:

  1. pip install tf-complex

Example use

You can define a complex convolution in the following way to use in one of your models:

  1. from tf_complex.convolutions import ComplexConv2D
  2. conv = ComplexConv2D(
  3. 16,
  4. 3,
  5. padding='same',
  6. activation='crelu',
  7. )