# Do not trust the LB,  trust your CV.  (5th/8th in public/private LB)

Congratulations to all the winners in this competition. Congratulate and thank my teammate Tom, earhian ,sheep and CHAN, It's memorable to team with you all.
Do not trust the LB, trust your CV. This is what I learned in this competition.
Our Model Design
1. binary classifier on ship/no ship (all images) -> resnet34, se-resnext50 based model
2. unet models (ship images only) 
3. unet models with deepsupervison (all images) 
4. mask rcnn (ship images only)
Our final submission combines results of different models above, details will be updated and some of our code will be on
[https://github.com/SeuTao/Kaggle_Airbus2018_8th_code](https://github.com/SeuTao/Kaggle_Airbus2018_8th_code)
PS: It's really lucky for us to survive the huge shakeup.
Actually pseudo labeling worked in this competition (single model 853 in private)