Dataset Versions

v6

2024-12-10 5:42pm

Generated on Dec 10, 2024

Dataset Split

Train Set 88%
3015Images
Valid Set 8%
262Images
Test Set 4%
131Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 320x240

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -6° and +6°
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1.1px
Noise: Up to 0.97% of pixels