Dataset Versions

v9

2024-03-26 5:04pm

Generated on Mar 26, 2024

Dataset Split

Train Set 88%
2172Images
Valid Set 8%
200Images
Test Set 4%
106Images

Preprocessing

Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -12° and +12°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -12% and +12%