Dataset Versions

v2

2024-03-30 4:13pm

Generated on Mar 30, 2024

Dataset Split

Train Set 90%
156Images
Valid Set 7%
12Images
Test Set 3%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 5 dropped

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%
Noise: Up to 0.7% of pixels