How can I use ViT?

[Shiming94]

Hi guys,

I have noticed that you have updated the VisionTransformer backbone, is there a network, that already uses it? I really want to see the performance of Transformer in Semantic Segmentation.

[clownrat6]

The relative configs are benchmarking. We may support vit+[fcn/deeplab/pspnet/upernet]. Please wait a minute. Furthermore, we will support SETR soon~.

[jianlong-yuan]

any news

[clownrat6]

If you are eager to use ViT for semantic segmentation, you can firstly refer to #520.

[Junjun2016]

Hi @jianlong-yuan and @Shiming94
We have released the SETR benchmark which is based on ViT.
And we will release other Transformer based semantic segmentation benchmarks ASAP.

[Shiming94]

Hi @jianlong-yuan and @Shiming94
We have released the SETR benchmark which is based on ViT.
And we will release other Transformer based semantic segmentation benchmarks ASAP.

Hey guy, Thanks soooo much! I will test it on our task. What a great contribution!