makanan Dataset

v2

2024-08-10 8:50am

Generated on Aug 10, 2024

Dataset Split

Train Set 91%
1400Images
Valid Set 5%
70Images
Test Set 5%
70Images

Preprocessing

Auto-Orient: Applied
Static Crop: 0-100% Horizontal Region, 0-90% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -10° and +10°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -20% and +20%
Brightness: Between -20% and +20%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.06% of pixels