Battery anomaly detection Computer Vision Model
219 Total Images
View All Images
Dataset Split
Train Set 92%
201Images
Valid Set 7%
15Images
Test Set 1%
3Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Blur: Up to 0.7px
Noise: Up to 0.1% of pixels