kwotsin/mimicry

[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

43
/ 100
Emerging

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.

generative-modeling deep-learning-research image-synthesis model-benchmarking reproducible-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

608

Forks

62

Language

Python

License

MIT

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.