30% AOT Dissolution Tracking Computer Vision Model
263 Total Images
View All Images
Dataset Split
Train Set 81%
213Images
Valid Set 10%
25Images
Test Set 9%
25Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Brightness: Between -30% and +30%
Blur: Up to 2px
Noise: Up to 1% of pixels