Dataset Versions
v3
2024-03-21 12:08am
Generated on Mar 21, 2024
18516 Total Images
View All Images
Dataset Split
Train Set 80%
14782Images
Valid Set 15%
2811Images
Test Set 5%
923Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 640x720
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 2
Crop: 1% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -15° and +15°
Hue: Between -25° and +25°
Saturation: Between -34% and +34%
Brightness: Between -8% and +8%
Exposure: Between -15% and +15%
Blur: Up to 4.9px
Noise: Up to 1.99% of pixels