Dataset Versions
v4
2024-12-17 12:18am
Generated on Dec 17, 2024
162 Total Images
View All Images
Dataset Split
Train Set 87%
141Images
Valid Set 8%
13Images
Test Set 5%
8Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 27% Maximum Zoom
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Blur: Up to 2.5px
Noise: Up to 1.96% of pixels