search

zju3dv / NeuralRecon

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
https://zju3dv.github.io/neuralrecon/
Apache License 2.0
2.03k stars 294 forks source link

Questions about training #61

Closed guozhongyuan-98 closed 2 years ago

guozhongyuan-98 commented 2 years ago

Thank you very much for sharing. I have some questions about training. 1、What data should I use to download scanet datasets? 2、What are the GPU requirements for training?

JiamingSuen commented 2 years ago
  1. You should download the entire dataset, not the semantic segmentation subset.
  2. Training with 8*V100 is preferred.