Dataset Versions

v4

2024-11-23 5:22pm

Generated on Nov 23, 2024

Dataset Split

Train Set 82%
3675Images
Valid Set 9%
409Images
Test Set 9%
407Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Hue: Between -15° and +15°
Saturation: Between -20% and +20%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Blur: Up to 2.5px
Noise: Up to 1% of pixels