Dataset Versions

v3

2024-10-30 1:14pm

Generated on Oct 30, 2024

Dataset Split

Train Set 92%
504Images
Valid Set 4%
21Images
Test Set 4%
21Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Brightness: Between -15% and +15%
Blur: Up to 1px
Noise: Up to 0.1% of pixels