Dataset Versions

v2

2022-02-11 5:43pm

Generated on Feb 11, 2022

Dataset Split

Train Set 96%
3585Images
Valid Set 1%
50Images
Test Set 3%
94Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Saturation: Between -20% and +20%
Brightness: Between -30% and +30%
Exposure: Between -25% and +25%
Blur: Up to 5px
Noise: Up to 2% of pixels

Similar Projects

See More