greeneggsandyaml

Ok, hopefully you'll be able to release it then!

Hello, I just wanted to follow up on this and give an update. I have tried with CUDA 11.1, with matching versions of CUDA, PyTorch, and pytorch-scatter. I still get...

Thanks for the response! I am using the main branch of DVGO (I just cloned, installed the dependencies, and tried to run `run.py`). I have not modified the code at...

Thanks for the investigation! I'm using gcc `5.4.0`, like in the issue that you linked. I will install a higher version of gcc and try again!

Amazing, thank you!

Hello authors, I just wanted to follow up on this issue.

Hello authors, I wanted to follow up on this again.

Update: Training nan'ed out after 20 epochs: Output log: ``` ... Epoch 15, global step 3375: val/loss_simple_ema was not in top 3 Epoch 16: 100%|█| 220/220 [13:47

If you could potentially post the log for one of the training runs, that would be very helpful for comparing results.

Thanks, I'll give it a try and report back on whether the instability persists with `--scale_lr False`.