Dataset Versions
v3
2023-08-10 10:26pm
Generated on Aug 10, 2023
7339 Total Images
View All Images
Dataset Split
Train Set 89%
6525Images
Valid Set 7%
543Images
Test Set 4%
271Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±13° Horizontal, ±23° Vertical
Grayscale: Apply to 25% of images
Hue: Between -71° and +71°
Blur: Up to 4px
Noise: Up to 20% of pixels
Cutout: 5 boxes with 18% size each