Kaleng1 Computer Vision Dataset
158 Total Images
View All Images
Dataset Split
Train Set 87%
138Images
Valid Set 8%
13Images
Test Set 5%
7Images
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, 55% Maximum Zoom
Rotation: Between -40° and +40°
Shear: ±33° Horizontal, ±20° Vertical
Grayscale: Apply to 100% of images
Hue: Between -167° and +167°
Saturation: Between -95% and +95%
Brightness: Between -65% and +65%
Exposure: Between -38% and +38%
Blur: Up to 4.8px
Noise: Up to 6.47% of pixels