final year project Computer Vision Model
336 Total Images
View All Images
Dataset Split
Train Set 97%
324Images
Valid Set 2%
8Images
Test Set 1%
4Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -88° and +88°
Noise: Up to 5% of pixels