Dataset Versions

v20

2024-02-21 9:33am

Generated on Feb 21, 2024

Dataset Split

Train Set 87%
627Images
Valid Set 10%
69Images
Test Set 3%
21Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 7% Maximum Zoom
Rotation: Between -10° and +10°
Shear: ±13° Horizontal, ±10° Vertical
Grayscale: Apply to 23% of images
Hue: Between -25° and +25°
Saturation: Between -28% and +28%
Brightness: Between -22% and +22%
Exposure: Between -13% and +13%
Blur: Up to 1.3px
Noise: Up to 1.45% of pixels
Bounding Box: Brightness: Between -12% and +12%
Bounding Box: Exposure: Between -12% and +12%

Similar Projects

See More
138 images 1 model