EdgeNeXt icon indicating copy to clipboard operation
EdgeNeXt copied to clipboard

Published 20 hours ago • verified publisher icon mmaaz60

EdgeNeXt for semantic segmentation

Open lkdci opened this issue 2 years ago • 5 comments

Hi, Thanks for your work. Is there any plan to share your implementation for semantic segmentation with PascalVOC dataset? Perhaps instructions on how to build the modules or pth checkpoints / onnx models?

lkdci avatar Jul 05 '22 11:07 lkdci

Hi @lkdci,

Thank you for your interest in our work. We do have plans to release segmentation codes and models, however it may take some time. Some extra details; we implemented our EdgeNeXt model in MobileViT for segmentation experiments. I am attaching the .pt checkpoints here in case it might be helpful for now. EdgeNeXt_DeepLabV3.zip

Thanks

mmaaz60 avatar Jul 05 '22 11:07 mmaaz60

Hi @mmaaz60, thanks for the fast reply. So basically the backbone remains the same, and an ASPP module is used as Decoder?

lkdci avatar Jul 06 '22 09:07 lkdci

Hi @mmaaz60, thanks for the fast reply. So basically the backbone remains the same, and an ASPP module is used as Decoder?

Hi @lkdci, yes you are right. Thanks

mmaaz60 avatar Jul 06 '22 09:07 mmaaz60

@mmaaz60 Hi, Can give more details? I am trying to use edgenext for semantic segmentation of bdd100k, but after training 160k, the effect is not satisfactory, do you use any auxiliary head?

AndPuQing avatar Sep 20 '22 12:09 AndPuQing

Hi @AndPuQing,

Apologies for the late reply. We do not use any auxiliary head. Did you try tuning your learning rate?

mmaaz60 avatar Oct 13 '22 05:10 mmaaz60