search

marcoaversa / diffinfinite

DiffInfinite Official Code
MIT License
30 stars 4 forks source link

unimported fct #4

Open joihn opened 7 months ago

joihn commented 7 months ago

thanks for this repo, This fct is non imported, thus undefined. https://github.com/marcoaversa/diffinfinite/blob/4d2309606e5ce6190828b96f436cfa962ec5d1ec/dm.py#L592

I guess one could import it from dm_masks.py:75

marcoaversa commented 7 months ago

Thanks for the feedback. We forgot to remove the normalise_to_neg_one_to_one function. In our case we manually normalise the latent by a factor instead of mapping the data into [-1,1]. This is because the data clipped in the VQVAE latent space were introducing biases in the colour of the synthetic images, we will fix it soon.

joihn commented 7 months ago

Thanks for the reply, I also noticed that my generated images are significantly brighter than the ground truth, maybe this could be the cause,

Looking forward for the fix :) ! Do you have an ETA ?

joihn commented 7 months ago

actually it looks like the fix is actually already present: image

image

marcoaversa commented 7 months ago

Yep! The factor 50 should be adapted to your own dataset. In our case 50 was a good value to limit the noise to go inside [-1,1] on each step. I would expect that I can fix and polish it properly in 3 weeks.

joihn commented 7 months ago

okay thanks