Dataset Versions

v3

2022-11-05 10:42am

Generated on Nov 5, 2022

Dataset Split

Train Set 93%
1734Images
Valid Set 5%
92Images
Test Set 2%
33Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±5° Horizontal, ±5° Vertical
Hue: Between -20° and +20°
Saturation: Between -20% and +20%
Brightness: Between -20% and +20%
Blur: Up to 1px
Noise: Up to 1% of pixels

Similar Projects

See More
400 images 1 model