TruNguyen

CTQT

Classification

CTQT Image Dataset

v1

2022-01-15 8:40pm

Generated on Jan 16, 2022

Dataset Split

Train Set 92%
8703Images
Valid Set 4%
363Images
Test Set 4%
363Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±4° Vertical
Blur: Up to 0.5px
Noise: Up to 3% of pixels