Dataset Versions

v2

2024-06-12 11:12am

Generated on Jun 12, 2024

Dataset Split

Train Set 95%
2040Images
Valid Set 4%
79Images
Test Set 1%
25Images

Preprocessing

Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Grayscale: Apply to 19% of images
Brightness: Between -22% and +22%
Exposure: Between -12% and +12%
Noise: Up to 0.18% of pixels

Similar Projects

See More