Dataset Versions
v1
2023-08-05 11:34pm
Generated on Aug 5, 2023
1092 Total Images
View All Images
Dataset Split
Train Set 92%
1008Images
Valid Set 4%
44Images
Test Set 4%
40Images
Preprocessing
Auto-Orient: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 41% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Hue: Between -83° and +83°
Saturation: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels