search

microsoft / CSWin-Transformer

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022
MIT License
539 stars 78 forks source link

Experiment setting for semantic segmentation #13

Closed AnukritiSinghh closed 2 years ago

AnukritiSinghh commented 3 years ago

Hi, thank you for the code. I implemented CSwin-T with FPN for semantic segmentation in ADE20K but couldn't reach the mIoU value of 48.2 as mentioned by you in the table. The maximum I could get was 39.9 mIoU, it will be great if you could share the exact experiment settings you used? Thanks

506813254 commented 3 years ago

Hi, thank you for the code. I implemented CSwin-T with FPN for semantic segmentation in ADE20K but couldn't reach the mIoU value of 48.2 as mentioned by you in the table. The maximum I could get was 39.9 mIoU, it will be great if you could share the exact experiment settings you used? Thanks

Hi, How do you solve the split size when the resolution of the input image is different? Can you take a look at the code?

LightDXY commented 2 years ago

code and models released, please create a new issue for any new problems.