Dataset Versions

v1

2024-10-08 3:15pm

Generated on Oct 8, 2024

Dataset Split

Train Set 92%
378Images
Valid Set 4%
16Images
Test Set 4%
16Images

Preprocessing

Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Blur: Up to 2.5px
Noise: Up to 1.76% of pixels