Dataset Versions
v4
2023-07-08 11:53am
Generated on Jul 8, 2023
92 Total Images
View All Images
Dataset Split
Train Set 85%
78Images
Valid Set 10%
9Images
Test Set 5%
5Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Modify Classes: 2 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 56% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±1° Horizontal, ±45° Vertical
Hue: Between -32° and +32°
Saturation: Between -99% and +99%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2px
Cutout: 6 boxes with 14% size each