# repeating topcoders unet results

Unet seems to be an important approach for future kaggle challenge as well. Hence I have decided to repeat topcoder results, making modifications if required. My target is 0.580 on public LB on stage1 dataset first. (there is an evaluation code in my code base for scoring your csv file against the released stage1 test solution csv)
My code base is at:
[https://drive.google.com/drive/folders/1EtBdlPK3BVahHBZtB103QQxNUdWaJ6di](https://drive.google.com/drive/folders/1EtBdlPK3BVahHBZtB103QQxNUdWaJ6di)
. It is based on pytorch.
It is still in progress. you can follow this thread for update.
The attached ppt shows current progress.
latest : 20180427 folder
unet (fpn se-resnext152 backbone)
learning watershed line as border