search

advimman / lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
https://advimman.github.io/lama-project/
Apache License 2.0
8.06k stars 855 forks source link

Evaluation Metrics #170

Closed alexerupakat closed 1 year ago

alexerupakat commented 2 years ago

Hai Can you tell me how the FID and other metrics are obtained . did you take the mean value ?

cohimame commented 1 year ago

Hello!

If you are asking how to compute the FID metric in general, check out this material: https://wandb.ai/ayush-thakur/gan-evaluation/reports/How-to-Evaluate-GANs-using-Frechet-Inception-Distance-FID---Vmlldzo0MTAxOTI

And original paper where the FID was introduced: https://papers.nips.cc/paper/2017/file/8a1d694707eb0fefe65871369074926d-Paper.pdf

We also cover a metrics question in the following section: https://github.com/saic-mdal/lama#places Screenshot_20221226_172828