train.py fail (preloads images to 95%)

NVlabs / neuralangelo

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

https://research.nvidia.com/labs/dir/neuralangelo/

Other

4.27k stars 383 forks source link

train.py fail (preloads images to 95%) #178

Closed MicKkmack closed 5 months ago

MicKkmack commented 6 months ago

Anyone able to help with the above train.py issue?

I've set the correct dict_size and dim for a 3070ti and I've tried reducing settings like iterations and batch size to see if that would help, but with no success.

MicKkmack commented 6 months ago

I've set preload in the base.yaml file to false and that seems to at least get it training, not sure if it'll cause issues

MicKkmack commented 5 months ago

Too many images , I had about 2400 images. I've tried around 100 images / 300 images / 600 images and that seems to be the sweat spot. At least for my 3070 graphics card