Giters

OpenGVLab / InternImage

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Home Page:https://arxiv.org/abs/2211.05778

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

GPU memory requirements increases when using DCNv3_pytorch rather than DCNv3

jonassoebro opened this issue · comments

commented

Thank you for this awesome implementation!

I've been using the InternImage as a backbone of my Detectron2 Faster-R-CNN implementation. My trained models need to run on CPU, so I tried making them compatible using the DCNv3_pytorch operator rather than the DCNv3. However the pytorch implementation seems to require a lot more GPU memory - is this expected or am I missing something?