The segment approach is based on the DeepLab v3 plus method, the original code implemented by pytorch can be found here.And the dataset used in this project is from the Kaggle Carvana Image Masking Challenge, the link is here.

Python(3.6) and Pytorch(0.4.1) is necessary before running the scripts. To install the required python packages(expect PyTorch), run

pip install -r requirements.txt