Dataset Versions
v3
2022-10-01 3:31pm
Generated on Oct 1, 2022
481 Total Images
View All Images
Dataset Split
Train Set 90%
432Images
Valid Set 10%
49Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 128x128
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±7° Horizontal, ±7° Vertical
Grayscale: Apply to 15% of images
Hue: Between -25° and +25°
Saturation: Between -22% and +22%
Brightness: Between -15% and +15%
Exposure: Between -15% and +15%
Blur: Up to 0.75px
Noise: Up to 6% of pixels