Dataset Versions
v3
2023-09-05 12:40pm
Generated on Sep 5, 2023
509 Total Images
View All Images
Dataset Split
Train Set 80%
405Images
Valid Set 12%
59Images
Test Set 9%
45Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -11° and +11°
Shear: ±19° Horizontal, ±18° Vertical
Grayscale: Apply to 100% of images
Hue: Between -29° and +29°
Saturation: Between -37% and +37%
Brightness: Between -16% and +16%
Exposure: Between -10% and +10%
Blur: Up to 1.5px
Noise: Up to 3% of pixels
Mosaic: Applied
Bounding Box: Shear: ±6° Horizontal, ±5° Vertical