Dataset Versions

v13

2024-11-22 3:05pm

Generated on Nov 22, 2024

Dataset Split

Train Set 94%
750Images
Valid Set 6%
52Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Static Crop: 9-87% Horizontal Region, 5-90% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 3% Maximum Zoom
Grayscale: Apply to 15% of images
Hue: Between -20° and +20°
Saturation: Between -30% and +30%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 2px
Noise: Up to 1.21% of pixels
Cutout: 4 boxes with 18% size each