drawing-type-classifier Computer Vision Model
3294 Total Images
View All Images
Dataset Split
Train Set 88%
2883Images
Valid Set 8%
274Images
Test Set 4%
137Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Shear: ±0° Horizontal, ±0° Vertical
Brightness: Between -15% and +15%
Noise: Up to 0.18% of pixels