Dataset Versions

v5

2022-07-28 10:03am

Generated on Jul 28, 2022

Dataset Split

Train Set 90%
1800Images
Valid Set 4%
80Images
Test Set 6%
111Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Auto-Adjust Contrast: Using Contrast Stretching
Modify Classes: 0 remapped, 2 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 7% Maximum Zoom
Hue: Between -12° and +12°
Saturation: Between -16% and +16%
Brightness: Between -25% and +25%
Blur: Up to 1px
Noise: Up to 1% of pixels
Mosaic: Applied