Dataset Versions

v3

augmented3x_80-20TrainTestSplit

Generated on Oct 24, 2022

Dataset Split

Train Set 92%
37347Images
Valid Set %
0Images
Test Set 8%
3122Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -12° and +12°
Grayscale: Apply to 10% of images
Hue: Between -20° and +20°
Saturation: Between -20% and +20%
Brightness: Between -20% and +20%
Exposure: Between -20% and +20%
Blur: Up to 0.75px
Noise: Up to 1% of pixels
Cutout: 6 boxes with 3% size each