SwinTransformer / Swin-Transformer-Semantic-Segmentation

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
https://arxiv.org/abs/2103.14030
Apache License 2.0
1.18k stars 222 forks source link

Unexpected keyword argument 'ape' #50

Closed TNA8 closed 3 years ago

TNA8 commented 3 years ago

When I run a demo using a pretrained model, I faced an error. What I run is python demo/image_demo.py test.png configs/swin/upernet_swin_tiny_patch4_window7_512_512_160k_ade20k.py moby_upernet_swin_tiny_patch4_window7_512*512.pth

Error is screenshot_4

miaochunle commented 3 years ago

I also encountered the same problem. How did you solve it

Joseph-149 commented 3 years ago

Reference issue 4, maybe the enviroment is incompatible. I solve it in the following way. cd Swin-Transformer-Semantic-Segmentation pip install -e .