Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Deyht/CIANNA
Convolutional Interactive Artificial Neural Networks by/for Astrophysicists
https://github.com/Deyht/CIANNA
astronomy astrophysics convolutional-neural-networks cuda deep-learning deep-neural-networks gpu machine-learning ml neural-network object-detection yolo
Last synced: 3 months ago
JSON representation
Convolutional Interactive Artificial Neural Networks by/for Astrophysicists
- Host: GitHub
- URL: https://github.com/Deyht/CIANNA
- Owner: Deyht
- License: apache-2.0
- Created: 2019-08-24T10:21:21.000Z (over 5 years ago)
- Default Branch: CIANNA
- Last Pushed: 2024-04-16T09:41:25.000Z (10 months ago)
- Last Synced: 2024-04-16T13:22:45.504Z (10 months ago)
- Topics: astronomy, astrophysics, convolutional-neural-networks, cuda, deep-learning, deep-neural-networks, gpu, machine-learning, ml, neural-network, object-detection, yolo
- Language: C
- Homepage:
- Size: 56.8 MB
- Stars: 24
- Watchers: 6
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome-yolo-object-detection - Deyht/CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists. (Other Versions of YOLO)
- awesome-yolo-object-detection - Deyht/CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists. (Other Versions of YOLO)
README
*Logo made by © Sarah E. Anderson*
### The first CIANNA release (V-1.0) is here! Check the [release page](https://github.com/Deyht/CIANNA/releases)!
## CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists
CIANNA is a general-purpose deep learning framework primarily developed and used for astronomical data analysis. Functionalities and optimizations are added based on relevance for astrophysical problem-solving. CIANNA can be used to build and train large neural network models for various tasks and is provided with a high-level Python interface (similar to keras, pytorch, etc.). One of the specificities of CIANNA is its custom implementation of a YOLO-inspired object detector used in the context of galaxy detection in 2D or 3D radio-astronomical data products. The framework is fully GPU-accelerated through low-level CUDA programming.
**Development team**
[David Cornu](https://vm-weblerma.obspm.fr/dcornu/) - creator and lead dev, post-doc researcher, AI Fellow PR[AI]RIE, FR - LERMA / Observatoire de Paris, PSL
Gregory Sainton - dev, AI Research engineer, FR - LERMA / Observatoire de Paris
Preferred contact point: [email protected]
See Copyright © and [License](#License) terms at the end.
## CIANNA application examples
Python scripts and Google-Colab-compatible notebooks are available under the [examples](https://github.com/Deyht/CIANNA/tree/CIANNA/examples) directory for most of the following examples.
| Description - Dataset | Visualization | Animation or real time |
| :---: | :---: | :---: |
| *** |
***Classical computer vision examples***
| *** |
| **Image classification
MNIST**
Top-1 accuracy ~99.3%
*Net. ~LeNet-5*
*630000 ips \@28p**
[](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/MNIST/mnist_train_notebook.ipynb) | 
|
| **Image classification
Imagenet - 1000 classes**
Top-1 acc ~74.7%
Top-5 acc ~91.7%
*Net. ~Darknet19*
*740 ips \@448p**
[](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/ImageNET/imagenet_pred_notebook.ipynb) | 
| 
|
| **Object detection
COCO - 1000 classes**
mAP\@50 ~40.1%
COCO-mAP ~21.9%
*Net. ~Darknet19*
*690 ips \@416p**
[](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/COCO/coco_pred_notebook.ipynb) | 
| 
*Real-time on a laptop GPU* |
| *** |
***Astronomical dataset examples***
| *** |
| **Source detection
SKA SDC1
2D continuum**
560MHz - 1000h
score 479372 pts
*Net. 17 conv. layers*
*500 ips \@512p**
[](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/SKAO_SDC1/sdc1_pred_notebook.ipynb)
[](https://ui.adsabs.harvard.edu/abs/2024A%26A...690A.211C/abstract) | 
| 
*Not real-time here, only animated* |
| **Profile regression
3D Galactic extinction mapping**
*Net. [C5x5.12-P2-{D3072}x2-D2048-D128]*
*120000 ips \@64p**
[](https://ui.adsabs.harvard.edu/abs/2022arXiv220105571C/abstract) | 
*Face-on view of the galactic plane in a 45° "cone" toward the Carina arm (derived from the 3D map)* | *Per LOS prediction examples*
*Integrated extinction skyview*
|
**Images (or Inputs) per second (ips) are given for an RTX 4090 GPU in inference using FP16C_FP32A mixed-precision at the specified resolution and with maximum batch size to saturate performances*.
###
## Installation
####
Please take a look at the [system requirements](https://github.com/Deyht/CIANNA/wiki/1\)-System-Requirements) and the [installation instructions](https://github.com/Deyht/CIANNA/wiki/2\)-Installation-instructions) wiki pages.
=> A complete **step-by-step installation guide** of CIANNA and its dependencies from a fresh Ubuntu 20.04 is accessible [here](https://github.com/Deyht/CIANNA/wiki/Step-by-step-installation-guide-\(Ubuntu-20.04\)).
## How to use
Please read the [How to use](https://github.com/Deyht/CIANNA/wiki/3\)-How-to-use-(Python-interface)) Wiki page for a minimalistic tour of CIANNA capabilities on a simple example script and dataset.
A full description of all the Python interface functions is available as an [API documentation](https://github.com/Deyht/CIANNA/wiki/4\)-Interface-API-documentation) page on the Wiki.
Please also consider consulting the [Step-by-step installation guide](https://github.com/Deyht/CIANNA/wiki/Step-by-step-installation-guide-\(Ubuntu-20.04\)) to verify everything was installed correctly.
Several Python scripts and notebooks are provided as [examples](https://github.com/Deyht/CIANNA/tree/CIANNA/examples) for different datasets and applications.
## Publications
List of known [publications](https://github.com/Deyht/CIANNA/wiki/Related-publications) that make use or directly refer to the CIANNA framework.
####
## Preferred citation method
When referring to a specific functionality or application, feel free to cite the relevant publication.
In all cases, if your work makes use of any version of CIANNA, please cite the non-version-specific DOI from Zenodo [10.5281/zenodo.12806324](https://doi.org/10.5281/zenodo.12806324).
####
###########################################################################
## License
These files are Copyright © 2024 [David Cornu](https://vm-weblerma.obspm.fr/dcornu/), but released under the [Apache2 License](https://github.com/Deyht/CIANNA/blob/master/LICENSE.md).
#### Contributor License Agreement
*While you are free to duplicate and modify this repository under the Apache2 License above, by being allowed to submit a contribution to this repository, you agree to the following terms:*
- *You grant to the present CIANNA framework (and its Author) your copyright license to reproduce and distribute your contributions and such derivative works.*
- *To the fullest extent permitted, you agree not to assert all of your "moral rights" in or relating to your contributions to the benefit of the present CIANNA framework.*
- *Your contribution was created in whole or in part by you and you have the right to submit it under the open source license indicated in the LICENSE file; or the contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open source license and you have the right to submit that work with modifications.*