kwotsin/mimicry
[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
Mimicry helps machine learning researchers confidently compare different Generative Adversarial Networks (GANs) without worrying about implementation inconsistencies. It provides standardized, pre-built GAN models and evaluation metrics, allowing researchers to input a dataset and receive performance scores that accurately reflect the GAN's capabilities. This ensures fair comparisons and reproducible research results for those working on generative models.
608 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher who needs to compare the performance of different GAN architectures and ensure your experimental results are reliable and reproducible.
Not ideal if you are an application developer looking for a high-level API to quickly integrate a GAN into an existing product without needing to understand the underlying research-level details.
Stars
608
Forks
62
Language
Python
License
MIT
Category
Last pushed
Aug 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kwotsin/mimicry"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch