Dataset Versions
v1
OverFitTest
Generated on May 21, 2024
5160 Total Images
View All Images
Dataset Split
Train Set 88%
4515Images
Valid Set 8%
430Images
Test Set 4%
215Images
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, 15% Maximum Zoom
Rotation: Between -5° and +5°
Shear: ±15° Horizontal, ±12° Vertical
Grayscale: Apply to 13% of images
Hue: Between -15° and +15°
Saturation: Between -32% and +32%
Brightness: Between -19% and +19%
Exposure: Between -13% and +13%
Blur: Up to 2.7px
Noise: Up to 0.85% of pixels