Rescue Detection Dataset

v5

2024-08-29 6:31am

Generated on Aug 29, 2024

Dataset Split

Train Set 94%
833Images
Valid Set 4%
34Images
Test Set 2%
16Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 7
Hue: Between -15° and +15°
Saturation: Between -24% and +24%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels

Similar Projects

See More