NVlabs / SegFormer

Official PyTorch implementation of SegFormer
https://arxiv.org/abs/2105.15203
Other
2.58k stars 357 forks source link

Could you share pretrain recipe? #138

Open sipie800 opened 1 year ago

sipie800 commented 1 year ago

I'm doing segmentation on very large images, which produce big flop even with your b0 scale. I decide to scale backbone to smaller one. IMO segformer can go smaller for some downstream tasks. But I believe your ImageNet pretrain is not done by some regular recipe like a ResNet one. Could you share hyperparameter details on MIT pretrain ?