Detection and Classification Dataset
Versions
v1
2024-08-16 9:35am
Generated on Aug 16, 2024
240 Total Images
View All Images
Dataset Split
Train Set 88%
210Images
Valid Set 7%
16Images
Test Set 6%
14Images
Preprocessing
Auto-Orient: Applied
Static Crop: 1-99% Horizontal Region, 1-99% Vertical Region
Resize: Stretch to 640x640
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 2% Maximum Zoom
Rotation: Between -2° and +2°
Shear: ±1° Horizontal, ±1° Vertical
Grayscale: Apply to 4% of images
Hue: Between -5° and +5°
Saturation: Between -9% and +9%
Brightness: Between -5% and +5%
Exposure: Between -2% and +2%
Blur: Up to 0.1px
Noise: Up to 0.02% of pixels