RealNOGADA Dataset

v4

2024-07-05 7:55pm

Generated on Jul 5, 2024

Dataset Split

Train Set 90%
11889Images
Valid Set 8%
1019Images
Test Set 2%
252Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x480

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Cutout: 2 boxes with 15% size each