Dataset Versions

v3

2024-10-03 10:56am

Generated on Oct 3, 2024

Dataset Split

Train Set 88%
432Images
Valid Set 8%
40Images
Test Set 4%
19Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Mosaic: Applied
Bounding Box: Flip: Horizontal
Bounding Box: Brightness: Between -15% and +15%