ymm

class

Classification

class Image Dataset

v2

2024-06-22 1:13pm

Generated on Jun 22, 2024

Dataset Split

Train Set 96%
549Images
Valid Set %
0Images
Test Set 4%
20Images

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, 58% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±13° Vertical
Grayscale: Apply to 15% of images
Hue: Between -23° and +23°
Saturation: Between -41% and +41%
Brightness: Between -64% and +64%
Exposure: Between -46% and +46%
Blur: Up to 3.9px
Noise: Up to 0.3% of pixels
Cutout: 7 boxes with 10% size each
smoke-types
30 images
Cigarette-box
49 images
dhr
liqun44-gGNL
171 images
yc
cigarette
37 images
dhr
ruanh
190 images