1999kevin

这个是个超声心动图数据集

I notice that your algorithm would return a gradient if setting return_gradients=True. Could you please give an explanation for what this gradients mean for a SDF. Does it mean the...

Hi, I'm a beginnger for meta-learning. As I know, it is used for fitting model across different data. In each epoch for meta-learning, there are a batch of tasks and...

Thank you for your excellent job. Now I want to configure this work on other dataset, NTIRE dataset for example. Could you please provide any hints on how to take...

How to run on a single linux server with multiple GPUs

12

Nice Job! I wonder how I can run the code on a single linux server with multiple GPUs. I can run the code on the server with one GPU by...

why applying Gaussian diffusion noise when converting latents to MLP weights

1

Hi, in your paper, I find that "after computing the sequence of latents, we apply Gaussian diffusion noise q(ht) to the latents with very little noise. After the noise and...

Nice job! I notice that you still use ReLU MLP with PE. A MLP architecture named SIREN, which replaces the ReLU activation to sine activation, has a better reprenentation ability....

Hi, I have checked your paper and codes, and find that your sampling strategy is different from that in SIREN. You only sample nl points within each block. But I...

Hi, thank you for your wonderful job. I have tested the performance on your models and get some trouble about the accuracy. Here is my test process: I have a...

Is it possible to provide any explanation about the lg_loss_scale?