Data

Tools

Indexes

Applications

Experiments

Open Source Science

cvnn

Library to help implement a complex-valued neural network (cvnn) using tensorflow as back-end

https://github.com/negu93/cvnn

Science Score: 77.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 3 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org, zenodo.org
  • ✓
    Committers with academic emails
    2 of 3 committers (66.7%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.3%) to scientific vocabulary

Keywords

complex-networks complex-neural-networks complex-numbers deep-learning machine machine-learning neural-networks python tensorflow
Last synced: 6 months ago · JSON representation ·

Repository

Library to help implement a complex-valued neural network (cvnn) using tensorflow as back-end

Basic Info
Statistics
  • Stars: 179
  • Watchers: 9
  • Forks: 36
  • Open Issues: 16
  • Releases: 4
Topics
complex-networks complex-neural-networks complex-numbers deep-learning machine machine-learning neural-networks python tensorflow
Created over 5 years ago · Last pushed 8 months ago
Metadata Files
Readme License Citation

README.md

Complex-Valued Neural Networks (CVNN)

Done by @NEGU93 - J. Agustin Barrachina

Documentation Status PyPI version Anaconda cvnn version DOI Downloads Stars Lines of Code

[!WARNING] This library is deprecated. In particular, it seems not to work correctly with TF version 2.16+.

Using this library, the only difference with a Tensorflow code is that you should use cvnn.layers module instead of tf.keras.layers.

This is a library that uses Tensorflow as a back-end to do complex-valued neural networks as CVNNs are barely supported by Tensorflow and not even supported yet for pytorch (reason why I decided to use Tensorflow for this library). To the authors knowledge, this is the first library that actually works with complex data types instead of real value vectors that are interpreted as real and imaginary part.

Update: - Since v1.12 (28 June 2022), Complex32 and Complex Convolutions in PyTorch. - Since v0.2 (25 Jan 2021) complexPyTorch uses complex64 dtype. - Since v1.6 (28 July 2020), pytorch now supports complex vectors and complex gradient as BETA. But still have the same issues that Tensorflow has, so no reason to migrate yet.

Documentation

Please Read the Docs

Instalation Guide:

Using Anaconda

conda install -c negu93 cvnn

Using PIP

pip install cvnn

Short example

From "outside" everything is the same as when using Tensorflow.

``` python import numpy as np import tensorflow as tf

Assume you already have complex data... example numpy arrays of dtype np.complex64

(trainimages, trainlabels), (testimages, testlabels) = get_dataset() # to be done by each user

model = get_model() # Get your model

Compile as any TensorFlow model

model.compile(optimizer='adam', metrics=['accuracy'], loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)) model.summary()

Train and evaluate

history = model.fit(trainimages, trainlabels, epochs=epochs, validationdata=(testimages, testlabels)) testloss, testacc = model.evaluate(testimages, test_labels, verbose=2) `` The main difference is that you will be usingcvnn` layers instead of Tensorflow layers. There are some options on how to do it as shown here:

Sequential API

``` py import cvnn.layers as complex_layers

def getmodel(): model = tf.keras.models.Sequential() model.add(complexlayers.ComplexInput(inputshape=(32, 32, 3))) # Always use ComplexInput at the start model.add(complexlayers.ComplexConv2D(32, (3, 3), activation='cartrelu')) model.add(complexlayers.ComplexAvgPooling2D((2, 2))) model.add(complexlayers.ComplexConv2D(64, (3, 3), activation='cartrelu')) model.add(complexlayers.ComplexMaxPooling2D((2, 2))) model.add(complexlayers.ComplexConv2D(64, (3, 3), activation='cartrelu')) model.add(complexlayers.ComplexFlatten()) model.add(complexlayers.ComplexDense(64, activation='cartrelu')) model.add(complexlayers.ComplexDense(10, activation='converttorealwith_abs'))
# An activation that casts to real must be used at the last layer. # The loss function cannot minimize a complex number return model ```

Functional API

``` python import cvnn.layers as complexlayers def getmodel(): inputs = complexlayers.complexinput(shape=(128, 128, 3)) c0 = complexlayers.ComplexConv2D(32, activation='cartrelu', kernelsize=3)(inputs) c1 = complexlayers.ComplexConv2D(32, activation='cartrelu', kernelsize=3)(c0) c2 = complexlayers.ComplexMaxPooling2D(poolsize=(2, 2), strides=(2, 2), padding='valid')(c1) t01 = complexlayers.ComplexConv2DTranspose(5, kernelsize=2, strides=(2, 2), activation='cart_relu')(c2) concat01 = tf.keras.layers.concatenate([t01, c1], axis=-1)

c3 = complex_layers.ComplexConv2D(4, activation='cart_relu', kernel_size=3)(concat01)
out = complex_layers.ComplexConv2D(4, activation='cart_relu', kernel_size=3)(c3)
return tf.keras.Model(inputs, out)

```

Project status

I currently work as a full-time employee and therefore the mantainance of this repository has been reduced or stopped. I would happily welcome anyone who wishes to fork the project or volunteer to step in as a maintainer or owner, allowing the project to keep going.

About me & Motivation

My personal website

I am a PhD student from Ecole CentraleSupelec with a scholarship from ONERA and the DGA

I am basically working with Complex-Valued Neural Networks for my PhD topic. In the need of making my coding more dynamic I build a library not to have to repeat the same code over and over for little changes and accelerate therefore my coding.

Cite Me

Alway prefer the Zenodo citation.

Next you have a model but beware to change the version and date accordingly.

bib @software{j_agustin_barrachina_2022_7303587, author = {J Agustin Barrachina}, title = {NEGU93/cvnn: Complex-Valued Neural Networks}, month = nov, year = 2022, publisher = {Zenodo}, version = {v2.0}, doi = {10.5281/zenodo.7303587}, url = {https://doi.org/10.5281/zenodo.7303587} }

Issues

For any issues please report them in here

This library is tested using pytest.

pytest logo

Owner

  • Name: J Agustin Barrachina
  • Login: NEGU93
  • Kind: user
  • Location: France
  • Company: SAFRAN Data Systems

Electronical Engineer with focus on Signal Processing. Interests: Voice Processing, Image Processing, Machine Learning.

Citation (citation.cff) 

cff-version: 1.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "BARRACHINA"
  given-names: "Jose Agustin"
  orcid: "https://orcid.org/0000-0002-2139-514X"
title: "Complex-Valued Neural Networks (CVNN)"
version: 1.0.3
doi: https://doi.org/10.5281/zenodo.4452131
date-released: 2019
url: "https://github.com/NEGU93/cvnn"

GitHub Events

Total
  • Issues event: 2
  • Watch event: 18
  • Issue comment event: 3
  • Push event: 3
  • Pull request event: 3
  • Fork event: 8
  • Create event: 2
Last Year
  • Issues event: 2
  • Watch event: 18
  • Issue comment event: 3
  • Push event: 3
  • Pull request event: 3
  • Fork event: 8
  • Create event: 2

Committers

Last synced: almost 3 years ago

All Time
  • Total Commits: 716
  • Total Committers: 3
  • Avg Commits per committer: 238.667
  • Development Distribution Score (DDS): 0.425
Top Committers
Name Email Commits
NEGU93 j****a@g****m 412
2019barrachija j****a@c****r 298
Joe Peetz j****z@d****u 6
Committer Domains (Top 20 + Academic)
dhcp-156-215.physics.ucla.edu: 1 centralesupelec.fr: 1

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 50
  • Total pull requests: 6
  • Average time to close issues: 24 days
  • Average time to close pull requests: 3 days
  • Total issue authors: 38
  • Total pull request authors: 4
  • Average comments per issue: 3.56
  • Average comments per pull request: 0.17
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 5
  • Pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 5
  • Pull request authors: 2
  • Average comments per issue: 2.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Karn3003 (3)
  • SantaTitular (3)
  • annabelleYan (3)
  • yanbowangbo (2)
  • jonasdaugalas (2)
  • mhsacampos (2)
  • ashkanee (2)
  • tahwaru (2)
  • teodorf-bit (2)
  • zeneggar (1)
  • j-peetz (1)
  • DiegoLigtenberg (1)
  • scuenat (1)
  • giuspillo (1)
  • osannolik (1)
Pull Request Authors
  • NEGU93 (5)
  • Angelld23 (2)
  • yonikl (2)
  • vandluke (1)
Top Labels
Issue Labels
feature request (4) bug (4) help wanted (4) waiting response (3) question (2) documentation (1)
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 196 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 85
  • Total maintainers: 1
pypi.org: cvnn

Library to help implement a complex-valued neural network (cvnn) using tensorflow as back-end

  • Versions: 85
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 196 Last month
Rankings
Stargazers count: 6.6%
Forks count: 7.6%
Downloads: 9.6%
Dependent packages count: 10.1%
Average: 11.1%
Dependent repos count: 21.5%
Maintainers (1)
negu93
Last synced: 6 months ago

Dependencies

docs/requirements.txt pypi
  • ipykernel *
  • nbsphinx *
setup.py pypi