Dataset Versions

v2

2024-05-17 3:59pm

Generated on May 17, 2024

Dataset Split

Train Set 80%
200Images
Valid Set 12%
30Images
Test Set 8%
20Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 2
Grayscale: Apply to 15% of images
Hue: Between -12° and +12°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.14% of pixels