lquirosd/P2PaLA

Wights used on the Website demo

imagine5am opened this issue · 1 comments

imagine5am commented

Hi
I used P2PaLA demo which you provide. Also, I downloaded the repo, pre-trained weights and everything. But I am getting very different results.

Is there some difference in configurations while running inference or is there some difference in pre-trained weights?
If there is a difference in pre-trained weights, can you share it?

lquirosd commented

Hi,

Hi
I used P2PaLA demo which you provide. Also, I downloaded the repo, pre-trained weights and everything. But I am getting very different results.

Is there some difference in configurations while running inference or is there some difference in pre-trained weights?

Yes, we train the demo model for a few more epochs, hence weights are different.

If there is a difference in pre-trained weights, can you share it?
Sorry but I cannot share the weights right now.

Regards,