wjf5203 / SeqFormer

SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About GPU RAM requirements

wenhe-jia opened this issue · comments

Not an issue, just asking about hardware requirements.

I am following you job to do VIS researching. But it came out with some limitation on GPU memory.
First, I run the SeqFormer/models/ops/test.py but after seconds the GPU memory is used out.
截屏2022-01-14 15 31 55
Then, I run the inference.py, everything went well at the beginning, when processing the 295th video, the GPU memory was used out again.
My machine is NVIDIA TITAN xp, can you tell me how much GPU RAM is required during inference time and running SeqFormer/models/ops/test.py?

Thanks for your attention.
Running SeqFormer/models/ops/test.py is not necessary.
During inference, around 15GB GPU RAM is required for ResNet-50 backbone.