Dataset Versions
v4
2023-12-29 12:15pm
Generated on Dec 29, 2023
386 Total Images
View All Images
Dataset Split
Train Set 92%
357Images
Valid Set 5%
19Images
Test Set 3%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 31% of images
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -31% and +31%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Mosaic: Applied