Dataset Versions

v3

2023-10-12 3:43pm

Generated on Oct 12, 2023

Dataset Split

Train Set 82%
393Images
Valid Set 9%
43Images
Test Set 9%
43Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -7° and +7°
Exposure: Between -22% and +22%
Blur: Up to 1.75px
Noise: Up to 5% of pixels
Cutout: 11 boxes with 3% size each