Giters

cleinc / bts

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Multi GPU training

sefibk opened this issue · comments

commented

Thank you for your interesting work and excellent reproduction code.

  1. Is the code fit for multiple GPU training?
  2. Did you experience any degradation in results?
  3. Should I change something in the arguments file or the command: 'python bts_main.py arguments_train_deci.txt'?
  • I am specifically referring to the NYU Pytorch training

Thanks a lot

commented

Could you tell me how many hours it takes to train with offered code on NYUDv2 24K or KITTI raw data such as with 4 GPU? Thanks! @sefibk

commented

It really depends on the model you are training. I was training my own proprietary one. And I don’t remember the how long it took. Sorry