smandava98
smandava98
Hi @nikhilaravi @HannaMao can we please get a clarification on this?
Okay, so apparently calling it directly without forward_features gives me the right vector and NOT cls_token from forward features. Still not sure what forward features does.
Hi @HannaMao can you please let us know how the demo results are much better than the model in the repo?
Hi @cmayer what points per side did you use? I counted the number of dots overlayed on the image in the web demo and there it is 32 points as...
Hi @Hippozhibos what values did you use to make yours work? Have you compared with results from the web demo? I am trying to simulate those same results but to...
Hi @HassanJbara how did you get it to predict the original x latent? I am confused, does the default code do that or does it predict noise?
Ah, I see the config now. Thanks. Did you ever figure out why you were getting different results for predicting noise vs predicting latents? What were the reasons for your...
Hi @davidzang0930 did you find any other ways to optimize it? If so can you please share?
I tried this on an 80 GB A100 as well as a 40 GB one and it runs out of memory for both (although it is allocating different sizes for...