search

pytorch / vision

Datasets, Transforms and Models specific to Computer Vision
https://pytorch.org/vision
BSD 3-Clause "New" or "Revised" License
16.16k stars 6.95k forks source link

pre-activation ResNet #205

Open bkj opened 7 years ago

bkj commented 7 years ago

Is there any interest in implementing the "pre-activation" version of ResNet, as described in

https://arxiv.org/pdf/1603.05027.pdf

and which has been show to have better performance on CIFAR 10/100 and Imagenet? It's a relatively minor modification of the ResNet version that's already implemented -- just changing the order of some of the operations in the residual block.

I'm happy to implement and submit a PR, though I don't really have the resources to train an Imagenet model ATM.

vfdev-5 commented 6 years ago

Any feedbacks on this ?

At least this could be good to implement BasicBlockV2 and BottleneckV2 as it is done in mxnet...

jlmckins commented 6 years ago

Any progress on this. It would be nice to have such a pretrained model for reproducing and starting from the work of others.

vfdev-5 commented 6 years ago

@jlmckins Implemented ResNetV2 in this PR but not yet trained.

fmassa commented 5 years ago

Another PR with pre-activation: https://github.com/pytorch/vision/pull/661

Tandon-A commented 1 year ago

Is there any progress on this?