Dataset Versions
Versions
v1
2023-04-05 8:35pm
Generated on Apr 5, 2023
120 Total Images
View All Images
Dataset Split
Train Set 88%
105Images
Valid Set 8%
10Images
Test Set 4%
5Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 31% Maximum Zoom
Rotation: Between -10° and +10°
Grayscale: Apply to 26% of images
Hue: Between -49° and +49°
Saturation: Between -48% and +48%
Brightness: Between -25% and +25%
Noise: Up to 4% of pixels
Cutout: 4 boxes with 12% size each