Dataset Versions

v10

2024-05-17 5:10pm

Generated on May 17, 2024

Dataset Split

Train Set 84%
21Images
Valid Set 8%
2Images
Test Set 8%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels
Bounding Box: Rotation: Between -15° and +15°

Similar Projects

See More
5 x
632 images
6 x
884 images
30 images 1 model
7 x
789 images
14 x
458 images