Closed chekirou closed 3 years ago
Solved by deleting the renderer in the unload function.
Hi.
I'm facing the same issue. Could you please elaborate on what exactly you did to solve the issue? Which unload function are you talking about?
Thanks in advance
Hi,
@alievk @seva100 do you have any pointers to solve this issue? I deleted the renderer and set it as None in the unload function (line 182 in /npbg/datasets/dynamic.py). While this solves the problem and I am able to train beyond the 1st epoch, the cpu ram usage and the gpu memory usage increases continuously and hence, I'm not able to train beyond 20 epochs at a time.
Thanks in advance
Hi @Shubhendu-Jena, unfortunately, I have never stumbled upon this issue. I can only suggest saving checkpoints regularly and restarting training from the latest checkpoint after it fails because of memory overflow...
Hi, I am trying to fit a scene and I have a problem with the dataloader. At the second epoch, even though the dataset is loaded, the scene.program seems to be None. Do you have an idea on where could the problem ?
Here is error message :
EPOCH 1