Dataset Versions
v3
2024-08-16 9:59pm
Generated on Aug 16, 2024
1492 Total Images
View All Images
Dataset Split
Train Set 94%
1400Images
Valid Set 4%
53Images
Test Set 3%
39Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 7
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Brightness: Between -18% and +18%
Blur: Up to 1.3px
Noise: Up to 0.38% of pixels
Bounding Box: Brightness: Between -15% and +15%