920232796/SETR-pytorch
Implementation of SETR model, Original paper: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers.
Python
Issues
- 2
多类分割问题
#10 opened by yuyunlong2002 - 0
请问这篇文章的模型和vit的不同只是在decoder部分吗?
#12 opened by hackerax - 0
有第二种解码器,即MLA上采样的代码嘛
#11 opened by panboshui - 0
收敛问题
#9 opened by Niu-yuchen - 0
具体效果
#8 opened by caihaunqai - 5
请问下作者,你训练carvana数据效果如何
#4 opened by JavisPeng - 3
- 1
have you pretrain model?
#6 opened by Hyerin-oh - 1
作者可以考虑提供一份可视化test代码吗
#5 opened by NightSongs - 12
关于setr输出
#3 opened by Peterchen111 - 3
请问关于模型的"img_size"这个参数是什么呀?不需要和输入一样吗?
#2 opened by GusRoth - 4
doubt about patch embeddings
#1 opened by zaocan666