romaine mendoza Computer Vision Model
Versions
108 Total Images
View All Images
Dataset Split
Train Set 94%
102Images
Valid Set 3%
3Images
Test Set 3%
3Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px