Dataset Versions
v2
2023-02-23 2:36pm
Generated on Feb 23, 2023
4600 Total Images
View All Images
Dataset Split
Train Set 90%
4140Images
Valid Set 7%
300Images
Test Set 3%
160Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 227x227
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Noise: Up to 5% of pixels