clean-fid
OASIS
| clean-fid | OASIS | |
|---|---|---|
| 3 | 1 | |
| 863 | 317 | |
| - | 2.5% | |
| 2.6 | 10.0 | |
| 2 months ago | over 1 year ago | |
| Python | Python | |
| MIT License | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
clean-fid
-
[D] A better way to compute the Fréchet Inception Distance (FID)
The Fréchet Inception Distance (FID) is a widespread metric to assess the quality of the distribution of a image generative model (GAN, Stable Diffusion, etc.). The metric is not trivial to implement as one needs to compute the trace of the square root of a matrix. In all PyTorch repositories I have seen that implement the FID (https://github.com/mseitzer/pytorch-fid, https://github.com/GaParmar/clean-fid, https://github.com/toshas/torch-fidelity, ...), the authors rely on SciPy's sqrtm to compute the square root of the matrix, which is unstable and slow.
-
[D] Are there any good FID and KID metrics implementations existing that are compatible with pytorch?
https://github.com/GaParmar/clean-fid/ is my goto. https://github.com/mseitzer/pytorch-fid isn't bad either.
-
[D] Comparing the efficiency of different GAN models
The best repo for FID (as far as I know) is this one: https://github.com/GaParmar/clean-fid
OASIS
-
StyleGAN-NADA: Blind Training and Other Wonders
Conclusion So this is how StyleGAN-NADA, a CLIP-guided zero-shot method for Non-Adversarial Domain Adaptation of image generators, works. Although the StyleGAN-NADA is focused on StyleGAN, it can be applied to other generative architectures such as OASIS and many others.
What are some alternatives?
pytorch-fid - Compute FID scores with PyTorch.
Deep-Exemplar-based-Video-Colorization - The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
SDEdit - PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations
Keras-GAN - Keras implementations of Generative Adversarial Networks.
torch-fidelity - High-fidelity performance metrics for generative models in PyTorch
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
Anime2Sketch - A sketch extractor for anime/illustration.
AdamP - AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
gangealing - Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
generative-evaluation-prdc - Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.
anycost-gan - [CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing