# 28th place solution

Overview
Emsemble 14models
Model architecture: Unet, Unet++
Encoder: resnest200e, resnest101e, efficientnet-b7
The region that over 1/2 labelers considered contrail is GT, but I created labels for the regions that over 0, 1/4, 1/2, and 3/4 labelers considered contrail.I trained the model to predict these four labels simultaneously.
![](assets/48782740cf6e4f7d90633fb2.png)
(
[dataset notebook](https://www.kaggle.com/code/welshonionman/dataset-ashcolor-4labels)
,
[training notebook](https://www.kaggle.com/code/welshonionman/gr-icrgw-training-with-ashcolor-4labels)
)
pseudo labeling
Augmentation
A.RandomRotate90
A.RandomBrightnessContrast
A.CoarseDropout
A.RandomGridShuffle