CardDetectionV3

CardDetectionV3

Object Detection

CardDetectionV3 Image Dataset

v4

2.

Generated on May 17, 2022

Popular Download Formats

Dataset Split

Train Set 98%
9702Images
Valid Set 2%
198Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 1
Shear: ±35° Horizontal, ±35° Vertical
Hue: Between -3° and +3°
Saturation: Between -45% and +45%
Exposure: Between -25% and +25%
Blur: Up to 3px
Noise: Up to 15% of pixels
Cutout: 3 boxes with 13% size each