Dataset Versions

v2

2024-07-13 3:11pm

Generated on Jul 13, 2024

Dataset Split

Train Set 92%
843Images
Valid Set 4%
39Images
Test Set 4%
35Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -10° and +10°
Hue: Between -15° and +15°
Brightness: Between -30% and +30%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels