Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jesperdramsch/keras-complex
Keras-Tensorflow implementation of complex-valued convolutional neural networks
https://github.com/jesperdramsch/keras-complex
cnn complex complex-numbers convolutional-neural-networks deep-learning keras keras-tensorflow neural-network tensorflow
Last synced: about 9 hours ago
JSON representation
Keras-Tensorflow implementation of complex-valued convolutional neural networks
- Host: GitHub
- URL: https://github.com/jesperdramsch/keras-complex
- Owner: JesperDramsch
- License: other
- Fork: true (ChihebTrabelsi/deep_complex_networks)
- Created: 2019-02-05T06:39:04.000Z (almost 6 years ago)
- Default Branch: main
- Last Pushed: 2024-12-10T09:48:29.000Z (about 1 month ago)
- Last Synced: 2025-01-10T19:52:41.952Z (13 days ago)
- Topics: cnn, complex, complex-numbers, convolutional-neural-networks, deep-learning, keras, keras-tensorflow, neural-network, tensorflow
- Language: Python
- Homepage:
- Size: 376 KB
- Stars: 130
- Watchers: 6
- Forks: 45
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE.md
- Citation: CITATION.cff
Awesome Lists containing this project
README
# Complex-Valued Neural Networks in Keras with Tensorflow
[](https://keras-complex.readthedocs.io/) [](https://github.com/JesperDramsch/keras-complex/actions/) [](https://pypi.python.org/pypi/keras-complex)   [](https://pypi.python.org/pypi/keras-complex) [](LICENSCE.md)
[Complex-valued convolutions](https://en.wikipedia.org/wiki/Convolution#Domain_of_definition) could provide some interesting results in signal processing-based deep learning. A simple(-ish) idea is including explicit phase information of time series in neural networks. This code enables complex-valued convolution in convolutional neural networks in [keras](https://keras.io) with the [TensorFlow](https://tensorflow.org/) backend. This makes the network modular and interoperable with standard keras layers and operations.
This code is very much in **Alpha**. Please consider helping out improving the code to advance together. This repository is based on the code which reproduces experiments presented in the paper [Deep Complex Networks](https://arxiv.org/abs/1705.09792). It is a port to Keras with Tensorflow-backend.
Requirements
------------
- numpy
- scipy
- scikit-learn
- tensorflow 2.X
Install requirements for computer vision experiments with pip:
```
pip install -r requirements.txt
```
Depending on your Python installation you might want to use anaconda or venv or other tools.
Installation
------------
```
pip install keras-complex
```
Usage
-----
Build your neural networks with the help of keras.
```
import complexnn
import keras
from keras import models
from keras import layers
from keras import optimizers
model = models.Sequential()
model.add(complexnn.conv.ComplexConv2D(32, (3, 3), activation='relu', padding='same', input_shape=(28, 28, 2)))
model.add(complexnn.bn.ComplexBatchNormalization())
model.add(layers.MaxPooling2D((2, 2), padding='same'))
model.compile(optimizer=optimizers.Adam(), loss='mse')
```
An example working implementation of an autoencoder can be found [here](https://github.com/JesperDramsch/Complex-CNN-Seismic/).
Complex Format of Tensors
-------------------------
This library assumes that complex values are split into two real-valued parts. The real-valued and complex-valued complement, also seen [in the Docs](https://keras-complex.readthedocs.io/math.html).
The tensors for a 2D complex tensor of 3x3, the look like:
```
[[[r r r],
[r r r],
[r r r]],
[i,i,i],
[i,i,i],
[i,i,i]]]
```
So multiple samples should then be arranged into `[r,r,r,i,i,i]`, which is also documented [in the Docs](https://keras-complex.readthedocs.io/math.html#implementation).
Citation
--------
Find the [CITATION file](/CITATION.cff) or cite this software version as:
```
@misc{dramsch2019complex,
title = {Complex-Valued Neural Networks in Keras with Tensorflow},
url = {https://figshare.com/articles/Complex-Valued_Neural_Networks_in_Keras_with_Tensorflow/9783773/1},
DOI = {10.6084/m9.figshare.9783773},
publisher = {figshare},
author = {Dramsch, Jesper S{\"o}ren and Contributors},
year = {2019}
}
```
Please cite the original work as:
```
@ARTICLE {Trabelsi2017,
author = "Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal",
title = "Deep Complex Networks",
journal = "arXiv preprint arXiv:1705.09792",
year = "2017"
}
```