Most of the configuration files that we provide are in folder configs. You just need to modify dataset root, vgg model weight and output directory. There are a few possibilities:
1. Modify configuration file and run
You can modify train_fcn32s.yml first and run following code
We are training these models on VOC2012 train.txt and testing on val.txt, and we also use torchvision pretrained vgg16 rather than caffe pretrained. So the results maybe are different from the origin paper.