Dataset Versions
v3
2024-11-19 2:38pm
Generated on Nov 19, 2024
1416 Total Images
View All Images
Dataset Split
Train Set 97%
1379Images
Valid Set 2%
25Images
Test Set 1%
12Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 7
Flip: Horizontal
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Cutout: 5 boxes with 23% size each
Mosaic: Applied
Bounding Box: Brightness: Between -49% and +49%
Bounding Box: Noise: Up to 5.01% of pixels