Dataset Versions

v10

2023-05-17 4:57pm

Generated on May 17, 2023

Dataset Split

Train Set 88%
2646Images
Valid Set 9%
264Images
Test Set 3%
100Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Rotation: Between -9° and +9°
Brightness: Between -18% and +18%
Blur: Up to 0.25px
Noise: Up to 1% of pixels

Similar Projects

See More
1.5k images 1 model