Dataset Versions
v4
2023-10-27 9:49am
Generated on Oct 27, 2023
489 Total Images
View All Images
Dataset Split
Train Set 92%
450Images
Valid Set 5%
26Images
Test Set 3%
13Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Hue: Between -25° and +25°
Saturation: Between -60% and +60%
Brightness: Between -35% and +35%
Exposure: Between -23% and +23%
Blur: Up to 3.25px
Noise: Up to 9% of pixels
Mosaic: Applied