Versions
v2
2024-12-14 2:49pm
Generated on Dec 14, 2024
483 Total Images
View All ImagesDataset Split
Train Set 88%
423Images
Valid Set 4%
20Images
Test Set 8%
40Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 19% Maximum Zoom
Shear: ±15° Horizontal, ±13° Vertical
Hue: Between -24° and +24°
Brightness: Between -12% and +12%
Noise: Up to 0.97% of pixels