Dataset Versions

v8

2024-04-29 11:40am

Generated on Apr 29, 2024

Dataset Split

Train Set 87%
726Images
Valid Set 8%
70Images
Test Set 4%
35Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -33° and +33°
Grayscale: Apply to 15% of images
Brightness: Between -15% and +15%