promo2 Computer Vision Model
6781 Total Images
View All Images
Dataset Split
Train Set 82%
5552Images
Valid Set 12%
811Images
Test Set 6%
418Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Random Sample: Include 100% train, 100% valid, 100% test
Augmentations
Outputs per training example: 2
90° Rotate: Applied
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels
Mosaic: Applied