search

wuhuikai / FastFCN

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.
http://wuhuikai.me/FastFCNProject
Other
838 stars 148 forks source link

add resnest and xception65 #74

Open tjj1998 opened 4 years ago

tjj1998 commented 4 years ago

Copy Resnest and xception65 from Pytorch-Encoding, and xception65 only can be used without pretrained models.

Pls be careful as there are many changes!!

I test it on my own server, and everything seems ok. As a caution, maybe you could test it by yourself first.My FastFCN

I don't change the Readme.md and *.sh. Maybe you can rectify it if you agree this request.

If the server resources are not tight, I will run the encnet+jpu+resnest101+pcontext and encnet+jpu_x+resnest101+pcontext, I will share you the results at issues or pull another request about Readme.md with my pth.tar.

Thanks for your work again.

wuhuikai commented 4 years ago

I can not merge it, since

  1. no pretrained model
  2. no training and testing
  3. lots of changes and I have no time to review

When I have time, I will review this commit.