Dataset Versions

v2

2024-01-30 9:27pm

Generated on Jan 31, 2024

Dataset Split

Train Set 88%
636Images
Valid Set 8%
60Images
Test Set 4%
30Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 21% Maximum Zoom
Shear: ±13° Horizontal, ±15° Vertical
Hue: Between -39° and +39°
Brightness: Between -4% and +4%
Blur: Up to 1.3px
Noise: Up to 0.89% of pixels

Similar Projects

See More
789 images 2 models