Sneaker Detection Micro Features Computer Vision Model
Versions
1570 Total Images
View All Images
Dataset Split
Train Set 88%
1374Images
Valid Set 8%
131Images
Test Set 4%
65Images
Preprocessing
Auto-Orient: Applied
Static Crop: 0-50% Horizontal Region, 16-75% Vertical Region
Resize: Stretch to 224x224
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Noise: Up to 0.82% of pixels
Motion Blur: Length 10px, Angle: 0°, Frames: 1