search

aofrancani / TSformer-VO

Implementation of the paper "Transformer-based model for monocular visual odometry: a video understanding approach".
https://arxiv.org/abs/2305.06121
MIT License
71 stars 11 forks source link

GPU #12

Closed 110sha closed 8 months ago

110sha commented 8 months ago

Hello, may I ask where to modify if I want to use GPUs 2 and 3 for training together? I couldn't find it, thank you!

aofrancani commented 8 months ago

Hi, I only use one GPU because I did the training in Google Colab and there is only one GPU in my lab. So I wasn't worried about that, sorry.

Maybe this link from the TimeSformer model can help to see where you need to modify the code: https://github.com/search?q=repo%3Afacebookresearch%2FTimeSformer%20NUM_GPUS&type=code

110sha commented 8 months ago

Okay, thank you for your reply. I will carefully read the TimeSformer code to find the modification location.