# 132th Solution: 2D UNet with p1-p99 normalization

A simple tu-seresnext50_32x4d UNet with volumes normalized on percentiles 1 and 99. The inference was a votation accumulation from x3 axis x4 rot90 scan of the minimum square possible padding with reflections. TH = 6 (of 12, .5)
[https://www.kaggle.com/code/sacuscreed/smp-2d-inference-back-to-basics?scriptVersionId=161523508](https://www.kaggle.com/code/sacuscreed/smp-2d-inference-back-to-basics?scriptVersionId=161523508)
The training was made on kidney_1_dense and kidney_3_dense 512x512 centred on labels centroid crops padded with reflections too and basic augmentations. Batches of 8 (4 of each kidney) during 50 epochs without validation:
[https://www.kaggle.com/code/sacuscreed/143th-solution](https://www.kaggle.com/code/sacuscreed/143th-solution)