search

YiLunLee / missing_aware_prompts

Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23
https://yilunlee.github.io/missing_aware_prompts/
160 stars 9 forks source link

Training settings #12

Closed hulianyuyy closed 1 year ago

hulianyuyy commented 1 year ago

Many thanks for your great work! May i ask how many GPUs are needed during training?

YiLunLee commented 1 year ago

Thank you for your question.

I use 2 NVIDIA GTX 2080Ti GPUs with per_gpu_batchsize=2 for MM-IMDb dataset. However, the number of GPUs depends on your choice. You can adjust the config per_gpu_batchsize and num_gpus to fit your environment.