Dataset Versions

v3

2024-05-08 9:10pm

Generated on May 8, 2024

Dataset Split

Train Set 89%
90Images
Valid Set 8%
8Images
Test Set 3%
3Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.5% of pixels