Dataset Versions

v4

2024-03-04 4:04pm

Generated on Mar 4, 2024

Dataset Split

Train Set 87%
867Images
Valid Set 8%
83Images
Test Set 4%
41Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -12° and +12°
Hue: Between -24° and +24°
Saturation: Between -61% and +61%
Blur: Up to 2.5px
Noise: Up to 1.76% of pixels