Dataset Versions
Versions
v3
2024-11-12 10:05pm
Generated on Nov 12, 2024
288 Total Images
View All ImagesDataset Split
Train Set 89%
255Images
Valid Set 9%
25Images
Test Set 3%
8Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 24% of images
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%