Dataset Versions

v1

2023-03-30 3:26pm

Generated on Mar 30, 2023

Dataset Split

Train Set 87%
411Images
Valid Set 8%
39Images
Test Set 4%
20Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -20° and +20°
Saturation: Between -70% and +70%
Brightness: Between -45% and +45%