How to train the network in three GPUs

sunset1995 / HorizonNet

Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.

https://sunset1995.github.io/HorizonNet/

MIT License

324 stars 88 forks source link

How to train the network in three GPUs #3

Open XGBoost opened 5 years ago

XGBoost commented 5 years ago

I have noticed you have mentioned that it takes four hours to finish the training on three NVIDIA GTX 1080 Ti GPUs. However, you do not describe how to train the network on three GPUs in README.md. When I run python train.py --id resnet50_rnn --use_rnn , it only takes a single GPU, and the batch size of it is eight which is different from that mentioned in your paper. Could you please describe the process of training in detail.

sunset1995 commented 5 years ago

Hi @XGBoost To train on multiple GPU, you have to modify few lines of code. You can check https://pytorch.org/tutorials/beginner/former_torchies/parallelism_tutorial.html This repo only work on single GPU.