Dataset Versions

v2

2024-12-22 12:09pm

Generated on Dec 22, 2024

Dataset Split

Train Set 94%
183Images
Valid Set 4%
7Images
Test Set 2%
4Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Grayscale: Apply to 15% of images
Hue: Between -41° and +41°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -15% and +15%
Blur: Up to 3.7px
Noise: Up to 0.42% of pixels