Dataset Versions
v2
2023-05-04 3:03pm
Generated on May 4, 2023
4769 Total Images
View All Images
Dataset Split
Train Set 88%
4173Images
Valid Set 8%
397Images
Test Set 4%
199Images
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
Shear: ±3° Horizontal, ±3° Vertical
Grayscale: Apply to 18% of images
Saturation: Between -91% and +91%
Brightness: Between -55% and +55%
Exposure: Between -12% and +12%
Blur: Up to 1.5px
Noise: Up to 2% of pixels
Cutout: 4 boxes with 5% size each