mmSegmentation的單GPU訓練和測試

mmSegmentation使用

• • mmSegmentation的使用
  • • • 參考：
      • mmseg安裝：
      • • 1. 安裝依賴包：
        • 2. mmcv 安裝
        • 3.mmseg安裝
      • mmseg 訓練
      • • 1. 單GPU
        • 2. 多GPU

mmSegmentation的使用

參考：

1. github

mmseg安裝：

1. 安裝依賴包：

python==3.6, 3.7
1.1.2<=mmcv<=1.2.0
torch==1.5.0 
torchvision==0.6.0

2. mmcv 安裝

CUDA	torch 1.6	torch 1.5	torch 1.4	torch 1.3
10.2	O	O	X	X
10.1	O	O	O	O
9.2	O	O	O	O
cpu	O	O	O	O

pip install mmcv-full==latest+torch1.6.0+cu102 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.5.0+cu102 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.6.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.5.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.4.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.3.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.6.0+cu92 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
pip install mmcv-full==latest+torch1.6.0+cpu -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html

# 安裝mmcv-full build時間較長
pip isntall -r requirements.txt
MMCV_WITH_OPS=1 pip install -e .

3.mmseg安裝

pip install -r requirements/build.txt
pip install -e .

mmseg 訓練

1. 單GPU

須要注意問題：

https://github.com/open-mmlab/mmdetection/issues/847.  SyncBN only works with distributed environment, you may either use tools/dist_test.sh or modify SyncBN to BN manually during testing.

修改方法：
將configs/_base_中的參數設置 SyncBN修改成BN

2. 多GPU

參考：github