Dataset Versions

v1

2022-12-02 5:27pm

Generated on Dec 2, 2022

Dataset Split

Train Set 88%
4092Images
Valid Set 8%
388Images
Test Set 4%
192Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Blur: Up to 10px
Cutout: 3 boxes with 10% size each