SICECs

sicec-define

Classification

sicec-define Image Dataset

v1

2023-04-06 4:56pm

Generated on Apr 6, 2023

Dataset Split

Train Set 92%
7984Images
Valid Set %
0Images
Test Set 8%
730Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 2
Flip: Horizontal
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -40° and +40°
Saturation: Between -35% and +35%
Brightness: Between -35% and +35%
Noise: Up to 5% of pixels