Baran Hashemi
Baran Hashemi
I have the same problem for FID and get the same error.
I also have a question. Shouldn't one normalize (Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) the input data to the inceptionv3W model?
Hmm, interesting. Is this such normalization crucial due to the fact that the InceptionV3 takes inputs as ((x-128)/128) and had been trained with these normalized inputs? I am asking since...
What was the solution?
Well, neither of them were solving this error on my side. I get this error when I use num_G_accumulations or num_D_accumulations more than 2.
Hello guys, what is your experience with reducing the attention channel to 32 or reducing the feature channels to 16 for 256*256?
@thoglu I think, I also have the same problem with: `pdf = jammy_flows.pdf("e1", "gg", conditional_input_dim=5, amortization_mlp_dims='64')` ` 1%|▌ | 70/12585 [00:00 8 log_pdf, _, _ = pdf(target.unsqueeze(1), conditional_input=conditional_input) 10 #...
@lucidrains What do you think of [https://www.arxiv.org/abs/2408.14915](https://www.arxiv.org/abs/2408.14915), in particular the DRA activation function for Continuous Transformers?
@lucidrains If you confirm, I can also open a PR for DRA.
@lucidrains kind reminder.