Dataset Versions

v3

2024-07-10 6:43am

Generated on Jul 10, 2024

Dataset Split

Train Set 88%
1617Images
Valid Set 8%
155Images
Test Set 4%
76Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%