Dataset Versions
Versions
v1
2023-10-30 10:29am
Generated on Oct 30, 2023
722 Total Images
View All Images
Dataset Split
Train Set 88%
633Images
Valid Set 8%
59Images
Test Set 4%
30Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 224x224
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -20° and +20°
Grayscale: Apply to 26% of images
Saturation: Between -27% and +27%
Brightness: Between -32% and +32%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 6% of pixels