Dataset Versions

v1

2023-12-31 5:05pm

Generated on Dec 31, 2023

Dataset Split

Train Set 92%
618Images
Valid Set 7%
45Images
Test Set 1%
10Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Rotation: Between -11° and +11°
Shear: ±3° Horizontal, ±5° Vertical
Grayscale: Apply to 11% of images
Blur: Up to 0.9px
Noise: Up to 0.78% of pixels

Similar Projects

See More