Dataset Versions

v6

4

Generated on Jan 16, 2024

Dataset Split

Train Set 88%
171Images
Valid Set 8%
16Images
Test Set 4%
8Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Shear: ±2° Horizontal, ±2° Vertical
Grayscale: Apply to 10% of images
Exposure: Between -15% and +15%
Mosaic: Applied