Wuhan University

cigcigarette detections

Object Detection

cigcigarette detections Image Dataset

v4

2023-08-11 9:07am

Generated on Aug 11, 2023

Popular Download Formats

Dataset Split

Train Set 91%
10155Images
Valid Set 9%
1001Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -30° and +30°
Shear: ±33° Horizontal, ±42° Vertical
Grayscale: Apply to 10% of images
Saturation: Between -50% and +50%
Brightness: Between -30% and +30%
Exposure: Between -30% and +30%
Blur: Up to 0.75px