Dataset Versions
v2
2024-07-21 5:47pm
Generated on Jul 21, 2024
2085 Total Images
View All Images
Dataset Split
Train Set 94%
1968Images
Valid Set 4%
79Images
Test Set 2%
38Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 14% Maximum Zoom
Rotation: Between -15° and +15°
Grayscale: Apply to 25% of images
Hue: Between -26° and +26°
Saturation: Between -34% and +34%
Brightness: Between -15% and +15%
Exposure: Between -14% and +14%
Blur: Up to 3.1px
Noise: Up to 1.33% of pixels