search

Harry-Zhi / semantic_nerf

The implementation of "In-Place Scene Labelling and Understanding with Implicit Scene Representation" [ICCV 2021].
Other
426 stars 56 forks source link

Training time for a scene #42

Closed WenM1222 closed 1 year ago

WenM1222 commented 1 year ago

I noticed in your paper that the model was trained for 200,000 iterations on a single RTX2080Ti GPU. Could you please provide an estimate of the time it took to complete this training?

Harry-Zhi commented 1 year ago

Hi. If no rendering for training and test images are required, it takes approximately 9-10 hours at most in my case. If you conduct rendering for visualization during training every 20k/50k steps, it may increases to 11-12 hours.