search

ifnspaml / SGDepth

[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
MIT License
200 stars 26 forks source link

GPUs requirements and training time #22

Closed dongfengxijian closed 3 years ago

dongfengxijian commented 3 years ago

Thank you for your great work! How many GPUs and how long I need to train SGDepth?

klingner commented 3 years ago

Hey, I usually train on one GPU (e.g., Tesla P100) and it takes approximately 40 hours. However, my bottleneck is still the data loading, so it might even be faster, depending on your hardware.

dongfengxijian commented 3 years ago

Hey, I usually train on one GPU (e.g., Tesla P100) and it takes approximately 40 hours. However, my bottleneck is still the data loading, so it might even be faster, depending on your hardware.

Thank you for your replying！