IC size classification Computer Vision Model
5477 Total Images
View All Images
Dataset Split
Train Set 88%
4788Images
Valid Set 8%
456Images
Test Set 4%
233Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -8° and +8°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -23° and +23°
Saturation: Between -15% and +15%
Noise: Up to 0.22% of pixels