Dataset Versions

v1

fire

Generated on Apr 18, 2024

Dataset Split

Train Set 87%
201Images
Valid Set 9%
21Images
Test Set 3%
8Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 3
Rotation: Between -32° and +32°
Brightness: Between -30% and +30%
Blur: Up to 2.3px
Noise: Up to 5.33% of pixels