Dataset Versions

v10

2025-01-13 5:15pm

Generated on Jan 13, 2025

Dataset Split

Train Set 88%
2973Images
Valid Set 8%
284Images
Test Set 4%
140Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 2.9px
Noise: Up to 1.92% of pixels

Similar Projects

See More