mli0603 / stereo-transformer

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)
Apache License 2.0
660 stars 107 forks source link

parallel train #34

Open yanziwei opened 3 years ago

yanziwei commented 3 years ago

I want to know how to train this model in parallel?

mli0603 commented 3 years ago

Hi @yanziwei

I only had 1 gpu so the code was not written for DPP by default. You need to wrap the model into DPP training pipeline following this tutorial: https://pytorch.org/tutorials/intermediate/ddp_tutorial.html

XiandaGuo commented 9 months ago

We have seamlessly integrated the contributions of the talented author, STTR, into OpenStereo(https://github.com/XiandaGuo/OpenStereo), enabling support for multi-GPU training. We invite you to explore and experience it firsthand!