class Computer Vision Dataset
Versions
1700 Total Images
View All Images
Dataset Split
Train Set 82%
1400Images
Valid Set 9%
150Images
Test Set 9%
150Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 224x224
Augmentations
Outputs per training example: 2
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Noise: Up to 0.1% of pixels