OpenGVLab / InternImage

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
https://arxiv.org/abs/2211.05778
MIT License
2.52k stars 234 forks source link

InternImage Real Time #187

Open EthanAbitbol3 opened 1 year ago

EthanAbitbol3 commented 1 year ago

Hello and thank you for your work ! I have a question about internimage segmentation. I would like to know if this model is suitable for real-time applications. As a beginner in this field, I have been wondering about the possibility of using depthwise separable convolution instead of the standard convolution. Have you considered this alternative?