# My solution with code Public 99.71  but Private 99.67  

Framework
: Tensorflow(Keras)
Network
: customized Unet referred to Wide Residual Network, Squeeze-and-Excitation Network
[https://github.com/fujisanx/kaggle/tree/master/Segmentation](https://github.com/fujisanx/kaggle/tree/master/Segmentation)
Training
: 640x960 (640x959 1px padding), rotation, horizontal flip, scaling, HSV change, ganma correction, random erase
Inference
: 640x960 ( crop 640x959 )  up size cv2.INTER_CUBIC
Validation
: one hold out 20% data
Test set predictions
: 3 model predictions ( a little different paramater NN ) with TTA (flips).
Hardware
: GTX1080ti x 1
Japanese blog
[http://zero-ai.hatenablog.com/entry/2017/09/28/200328](http://zero-ai.hatenablog.com/entry/2017/09/28/200328)