Dataset Versions

v5

2023-03-20 3:05pm

Generated on Mar 20, 2023

Dataset Split

Train Set 86%
315Images
Valid Set 8%
28Images
Test Set 7%
24Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 224x224
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Grayscale: Apply to 25% of images
Brightness: Between -12% and +12%
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Noise: Up to 8% of pixels