SEG LIQUID Computer Vision Model
354 Total Images
View All Images
Dataset Split
Train Set 93%
329Images
Valid Set 6%
20Images
Test Set 1%
5Images
Preprocessing
Resize: Stretch to 320x320
Augmentations
Outputs per training example: 3
Rotation: Between -5° and +5°
Grayscale: Apply to 20% of images
Blur: Up to 2px