Dataset Versions

v12

2023-03-18 8:24pm

Generated on Mar 18, 2023

Dataset Split

Train Set 88%
1065Images
Valid Set 8%
100Images
Test Set 4%
51Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±5° Horizontal, ±5° Vertical
Grayscale: Apply to 16% of images
Saturation: Between -40% and +40%
Exposure: Between -25% and +25%
Blur: Up to 1px

Similar Projects

See More
9.4k images 1 model