Updated 9 months ago

nrel-sup3r • Rank 12.1 • Science 77%

The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial networks to create synthetic high-resolution wind and solar spatiotemporal data from coarse low-resolution inputs.

Updated 9 months ago

mmagic • Rank 20.5 • Science 54%

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

Updated 9 months ago

bmusegan • Rank 5.2 • Science 64%

Code for “Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation”

Updated 9 months ago

https://github.com/beegass/cs-541-deep-learning • Rank 3.4 • Science 23%

CS-541 Deep Learning is a graduate class that teaches both a theoretical and practical approach to deep learning. You will be able to see this in the different homework files in the form of workable code that can be tested as well as proofs and explanations as to where the code is coming from.

Updated 9 months ago

https://github.com/astorfi/cor-gan • Rank 4.8 • Science 10%

:unlock: COR-GAN: Correlation-Capturing Convolutional Neural Networks for Generating Synthetic Healthcare Records

Updated 9 months ago

https://github.com/chenliu-1996/gan-evaluator • Rank 3.2 • Science 10%

A pip-installable evaluator for GANs (IS and FID). Accepts either dataloaders or individual batches. Supports on-the-fly evaluation during training. A working DCGAN SVHN demo script provided.

Updated 9 months ago

evan • Rank 3.0 • Science 10%

:mag: python package to evaluate GANs for video generation

Updated 9 months ago

https://github.com/cptanalatriste/celebrity-generator • Rank 2.6 • Science 10%

A deep convolutional generative adversarial network (DCGAN) for generating faces.

Updated 9 months ago

https://github.com/christophreich1996/multi-stylegan • Science 10%

Official and maintained implementation of the paper "Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy" [MICCAI 2021].

Updated 9 months ago

style_transfer_gan_project • Science 54%

To ensure a better diagnosis of patients, doctors may need to look at multiple MRI scans. What if only one type of MRI needs to be done and others can be auto-generated? Generative Adversarial Networks (GANs) have been used for generating deepfakes, new fashion styles and high-resolution pictures from the low-resolution ones

Updated 9 months ago

mmgeneration • Science 44%

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

Updated 9 months ago

https://github.com/cedrickchee/relativisticgan • Science 10%

Code for replication of the paper "The relativistic discriminator: a key element missing from standard GAN"

Updated 9 months ago

awesome-data-synthesis • Science 67%

A curated list of awesome resources for creating synthetic data

Updated 9 months ago

argan • Science 39%

[Open Source]. ARGAN - The improved version of AnimeGAN. Landscape photos/videos to anime

Updated 9 months ago

physics-guided-dic-gan • Science 67%

Physics-guided generative adversarial network for interpolated digital image correlation data

Updated 9 months ago

deepbedmap • Science 23%

Going beyond BEDMAP2 using a super resolution deep neural network. Also a convenient flat file data repository for high resolution bed elevation datasets around Antarctica.

Updated 9 months ago

chimeramix • Science 67%

Official PyTorch implementation for ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing (IJCAI 2022)

Updated 9 months ago

multiscale-adversarial-attention-gates • Science 67%

Code for the paper: Valvano G. et al. (2021), Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates

Updated 9 months ago

seer • Science 57%

A GAN (generative adversarial network) for projecting synthetic building performance profiles.

Updated 9 months ago

https://github.com/cptanalatriste/birds-of-british-empire • Science 10%

Generating images of "fantastic" birds, using Generative Adversarial Networks (GANs).