github地址:https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation
Ubuntu的环境配置相对简单一些,
1、创建虚拟环境
conda create -n open-mmlab python=3.7
conda activate open-mmlab
2、安装pytorch
根据电脑的cuda版本选择pytorch,我试了1.6.0版本的可以。其他的版本在安装mmcv的时候有可能会出现问题。
3、安装mmcv-full
pip install -U torch1.6.0+cu101 torchvision0.7.0+cu102 -f https://download.pytorch.org/whl/torch_stable.html
4、下载并安装Swin-Transformer-Semantic-Segmentation
git clone https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation
cd Swin-Transformer-Semantic-Segmentation
pip install -e . #或者 pyhton setup.py develop。注意-e后面还有个. 不要丢掉。
1、下载预训练模型
ADE20K
| Backbone | Method | Crop Size | Lr Schd | mIoU | mIoU (ms+flip) | #params | FLOPs | config | log | model |
| — | — | — | — | — | — | — | — | — | — | — |
| Swin-T | UPerNet | 512x512 | 160K | 44.51 | 45.81 | 60M | 945G | [config](file:/D:/cv/Swin-Transformer-Semantic-Segmentation-main/configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k.py) | github/baidu | github/baidu |
| Swin-S | UperNet | 512x512 | 160K | 47.64 | 49.47 | 81M | 1038G | [config](file:/D:/cv/Swin-Transformer-Semantic-Segmentation-main/configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k.py) | github/