vision icon indicating copy to clipboard operation
vision copied to clipboard

Implementing and training SE-ResNet and SE-ResNeXt and including them in "torchvision.models"

Open talcs opened this issue 4 years ago • 3 comments

🚀 Feature

Inclusion of pretrained SE-ResNet and SE-ResNeXt models in torchvision.

Motivation

SE-ResNet and SE-ResNeXt outperform ResNet and ResNeXt respectively and have been released around 2 years ago already.

Pitch

Implementing SE blocks and creating ResNet and ResNeXt models that include them, which will be called SE-ResNet and SE-ResNeXt and will be available as a part of torchvision.models. The SE paper has been published in CVPR 2018.

Alternatives

Additional context

talcs avatar May 04 '20 14:05 talcs

@fmassa how do you think about those pretrained models?

zhangguanheng66 avatar May 04 '20 16:05 zhangguanheng66

Is this something still wanted? I am doing it either way, and if maintainers see this as a relevant addition I may open the pull request.

carlostojal avatar Jan 16 '24 20:01 carlostojal

Thanks for offering to help @carlostojal - at this point we have no plan to include these models in torchvision

NicolasHug avatar Jan 17 '24 10:01 NicolasHug