Dataset Versions
v5
2022-08-12 1:39pm
Generated on Aug 12, 2022
2701 Total Images
View All Images
Dataset Split
Train Set 88%
2364Images
Valid Set 8%
225Images
Test Set 4%
112Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x240
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Saturation: Between -15% and +15%
Brightness: Between 0% and +15%
Exposure: Between -1% and +1%