nourhene-ben-othmen

objects

Classification

objects Image Dataset

v1

2023-05-18 1:31pm

Generated on May 18, 2023

Dataset Split

Train Set 94%
204Images
Valid Set 4%
9Images
Test Set 2%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -27° and +27°
Shear: ±16° Horizontal, ±19° Vertical
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -18% and +18%
Noise: Up to 2% of pixels