nails_segmentation Computer Vision Model
15809 Total Images
View All Images
Dataset Split
Train Set 90%
14229Images
Valid Set 8%
1265Images
Test Set 2%
315Images
Preprocessing
Resize: Fit (white edges) in 512x512
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Grayscale: Apply to 24% of images
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Noise: Up to 1.96% of pixels