Dataset Versions

v16

2023-10-10 11:56pm

Generated on Oct 11, 2023

Dataset Split

Train Set 88%
495Images
Valid Set 9%
50Images
Test Set 3%
18Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 640x640
Grayscale: Applied
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -25° and +25°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Blur: Up to 1.5px
Noise: Up to 3% of pixels
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical

Similar Projects

See More
500 images 1 model