Use multi-GPU to calc FID score #17302
Unanswered
DQSSSSS
asked this question in
DDP / multi-GPU / multi-node
Replies: 1 comment 1 reply
-
Have you found a solution to this problem? I currently have an issue with how to test FID using PyTorch Lightning. Taking the CelebA dataset as an example, if I write a dataloader to iterate through the entire dataset as the validation set, how can we control the number of generated fake images for each val_step? |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I'm training the diffusion model and I want to calculate the FID score for each some steps.
Because the FID calculation needs to generate so many samples, e.g. 5000, I hope to distribute them to each GPU.
I know I can create a
Callback
class and implement it inon_validation_epoch_start
: generate 5000 samples, get the result, and log it, but it's on a single GPU.Beta Was this translation helpful? Give feedback.
All reactions