https://github.com/torchcvnn/torchcvnn
Pytorch layers for Complex Valued Neural Networks
https://github.com/torchcvnn/torchcvnn
complex-neural-networks complex-valued-neural-networks neural-networks python python3 pytorch
Last synced: 5 months ago
JSON representation
Pytorch layers for Complex Valued Neural Networks
- Host: GitHub
- URL: https://github.com/torchcvnn/torchcvnn
- Owner: torchcvnn
- License: mit
- Created: 2023-09-30T16:11:27.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2026-02-11T18:06:27.000Z (5 months ago)
- Last Synced: 2026-02-11T21:41:13.864Z (5 months ago)
- Topics: complex-neural-networks, complex-valued-neural-networks, neural-networks, python, python3, pytorch
- Language: Python
- Homepage: https://torchcvnn.github.io/torchcvnn/
- Size: 7.79 MB
- Stars: 31
- Watchers: 2
- Forks: 9
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Complex-Valued Neural Networks (CVNN) - Pytorch
[](https://torchcvnn.github.io/torchcvnn/)  [](https://badge.fury.io/py/torchcvnn)
**Documentation** [https://torchcvnn.github.io/torchcvnn/](https://torchcvnn.github.io/torchcvnn/)
**Examples** [https://www.github.com/torchcvnn/examples](https://www.github.com/torchcvnn/examples)
This is a library that uses [pytorch](https://pytorch.org) as a back-end for complex valued neural networks. It provides :
- complex valued datasets from remote sensing and MRI,
- complex valued transforms,
- complex valued layers, some of them requiring specific implementations because their computation is specific with complex valued activations, others are implemented merely because the lower level implementation raise an exception if processing complex valued activations even though the computations are the same than for real valued activations
- complex valued neural networks
It was initially developed by Victor Dhédin and Jérémie Levi during their third year project at CentraleSupélec.
## Installation
To install the library, it is simple as :
```
python -m pip install torchcvnn
```
or, using [uv](https://docs.astral.sh/uv/) :
```
uv pip install torchcvnn
```
## Other projects
You might also be interested in some other projects:
Tensorflow based :
- [cvnn](https://github.com/NEGU93/cvnn) developed by colleagues from CentraleSupélec
Pytorch based :
- [cplxmodule](https://github.com/ivannz/cplxmodule)
- [complexPyTorch](https://github.com/wavefrontshaping/complexPyTorch)
- [complextorch](https://github.com/josiahwsmith10/complextorch)