Dataset Versions

v1

336 na

Generated on Nov 29, 2024

Dataset Split

Train Set 88%
357Images
Valid Set 8%
34Images
Test Set 4%
17Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Brightness: Between -15% and +15%
Exposure: Between -8% and +8%
Blur: Up to 0.5px
Noise: Up to 0.18% of pixels