Dataset Versions

v10

2024-05-18 4:14pm

Generated on May 18, 2024

Dataset Split

Train Set 91%
306Images
Valid Set 9%
31Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Grayscale: Apply to 6% of images
Hue: Between -6° and +6°
Saturation: Between -5% and +5%
Brightness: Between -6% and +6%
Exposure: Between -4% and +4%
Blur: Up to 0.9px
Noise: Up to 1.05% of pixels