Dataset Versions

v3

2023-05-18 9:26am

Generated on May 18, 2023

Dataset Split

Train Set 88%
1812Images
Valid Set 8%
174Images
Test Set 4%
82Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Rotation: Between -10° and +10°
Saturation: Between -25% and +25%
Brightness: Between -37% and +37%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 3% of pixels

Similar Projects

See More