Maka_1_identify Computer Vision Model
5738 Total Images
View All Images
Dataset Split
Train Set 86%
4902Images
Valid Set 6%
357Images
Test Set 8%
479Images
Preprocessing
Auto-Orient: Applied
Augmentations
Outputs per training example: 3
Saturation: Between -15% and +15%
Brightness: Between -30% and +30%
Noise: Up to 1% of pixels
Cutout: 9 boxes with 2% size each