clean-fid

clean-fid copied to clipboard

Hello, I think the following implementation of the Fréchet distance is faster than the current one and would allow to drop the `scipy` dependency. ```python def frechet_distance(mu_x: Tensor, sigma_x: Tensor,...

francois-rozet

I'm very new to all this so this question might not make sense, but am I right in the assumption that FID relies on some pretrained model to evaluate the...

Seedmanc

Thanks for this excellent repository. Comparing with https://github.com/mseitzer/pytorch-fid, I would like to extract features from different pooling layers like the first max pooling features (64), second max pooling features (192),...

sivaramakrishnan-rajaraman

cuda device mismatch in `DataParallel` when not using `cuda:0`

1

Hi there, thanks for this package, it's really helpful! On a cluster with multiple GPUs, I have my model on device `cuda:1`. When calculating FID with a passed `gen` function,...

janfb

FID scores of many generated images from a single input image

1

Hi, thanks for your work, I wanted to calculate the FID score between multiple generations of the same input image. I setup my directories such that directory 1 contains n...

Ashh-Z

jwong8314