Dataset Versions
v1
1st hope
Generated on Sep 15, 2024
6789 Total Images
View All Images
Dataset Split
Train Set 82%
5588Images
Valid Set 12%
803Images
Test Set 6%
398Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 2
Rotation: Between -4° and +4°
Grayscale: Apply to 10% of images
Saturation: Between -30% and +30%
Brightness: Between -25% and +25%
Exposure: Between -10% and +10%