Dataset Versions
v2
2024-03-20 5:32pm
Generated on Mar 20, 2024
1272 Total Images
View All Images
Dataset Split
Train Set 88%
1119Images
Valid Set 8%
103Images
Test Set 4%
50Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 9% Minimum Zoom, 24% Maximum Zoom
Saturation: Between -10% and +10%
Brightness: Between -14% and +14%
Exposure: Between -8% and +8%
Noise: Up to 0.28% of pixels