• Stars
    star
    196
  • Rank 198,553 (Top 4 %)
  • Language
    Python
  • License
    Other
  • Created about 4 years ago
  • Updated 7 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Generative AI Image Toolset with GANs and Diffusion for Real-World Applications

License Docs Website

Generative AI Image Toolset with GANs and Diffusion for Real-World Applications

JoliGEN is an integrated framework for training custom generative AI image-to-image models

Main Features:

  • JoliGEN implements both GAN and Diffusion models for unpaired and paired image to image translation tasks, including domain and style adaptation with conservation of semantics such as image and object classes, masks, ...

  • JoliGEN generative AI capabilities are targeted at real world applications such as Controled Image Generation, Augmented Reality, Dataset Smart Augmentation and object insertion, Synthetic to Real transforms.

  • JoliGEN allows for fast and stable training with astonishing results. A server with REST API is provided that allows for simplified deployment and usage.

  • JoliGEN has a large scope of options and parameters. To not get overwhelmed, follow the simple Quickstarts. There are then links to more detailed documentation on models, dataset formats, and data augmentation.

Useful links

Use cases

  • AR and metaverse: replace any image element with super-realistic objects
  • Image manipulation: seamlessly insert or remove objects/elements in images
  • Image to image translation while preserving semantics, e.g. existing source dataset annotations
  • Simulation to reality translation while preserving elements, metrics, ...
  • Image generation to enrich datasets, e.g. counter dataset imbalance, increase test sets, ...

This is achieved by combining powerful and customized generator architectures, bags of discriminators, and configurable neural networks and losses that ensure conservation of fundamental elements between source and target images.

Example results

Image translation while preserving the class

Mario to Sonic while preserving the action (running, jumping, ...)

Clipboard - June 6, 2022 9 44 PM Clipboard - June 5, 2022 12 02 PM

Object insertion

Car insertion (BDD100K) with Diffusion image image

Glasses insertion (FFHQ) with Diffusion

drawing drawing

Object removal

Glasses removal with GANs

Clipboard - November 9, 2022 4_33 PM Clipboard - November 9, 2022 10_40 AM

Style transfer while preserving label boxes (e.g. cars, pedestrians, street signs, ...)

Day to night (BDD100K) with Transformers and GANs image

Clear to snow (BDD100K) by applying a generator multiple times to add snow incrementally image

Clear to overcast (BDD100K) image

Clear to rainy (BDD100K) image image

Features


Code format and Contribution

If you want to contribute please use black code format. Install:

pip install black 

Usage :

black .

If you want to format the code automatically before every commit :

pip install pre-commit
pre-commit install

Authors

JoliGEN is created and developed by Jolibrain.

Code structure is inspired by pytorch-CycleGAN-and-pix2pix, CUT, AttentionGAN, MoNCE, Palette among others.

Elements from JoliGEN are supported by the French National AI program "Confiance.AI"

Contact: [email protected]

More Repositories

1

deepdetect

Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
C++
2,520
star
2

dd_performances

DeepDetect performance sheet
Python
92
star
3

fluidnet_cxx

FluidNet re-written with ATen tensor lib
C++
51
star
4

livedetect

Live video client to DeepDetect
Go
50
star
5

wheatley

Next-generation scheduling problem solver based on GNNs and Reinforcement Learning
Python
20
star
6

platform_ui

Web interface to control DeepDetect process
JavaScript
11
star
7

deepdetect-js

DeepDetect javascript client
JavaScript
8
star
8

dd_platform_docker

DeepDetect Platform Dockerfile
Shell
8
star
9

gpustat_server

`gpustat` JSON server
Python
8
star
10

recognition

This is the source code of the backend and online parts of the IK Prize 2016 Recognition projects with Tate Britain, Fabrica and Microsoft
JavaScript
6
star
11

godd

🧠 DeepDetect package for easy integration in any Go project
Go
5
star
12

vicreg-loss

Pytorch implementation of the VICReg loss.
Python
4
star
13

dd_board

Tensorboard logger for DeepDetect server JSON output
Python
4
star
14

platform_data

Jupyter Notebook
3
star
15

libtscaling

Temperature scaling for neural network calibration
C++
3
star
16

ddapi

DeepDetect API Documentation
JavaScript
3
star
17

libvnn

C++ gstreamer-based video streaming library to deep nets with GPU support
C++
3
star
18

dd_ami_tools

DeepDetect AMI Tools
Python
3
star
19

dd_widgets

DeepDetect Python Jupyter Notebook Widgets
Python
3
star
20

platform_annotations

VoTT fork with DeepDectect connector, open source annotation and labeling tool for image and video assets
TypeScript
1
star