Yisong Li

125

Instance Segmentation

125 Image Dataset

v1

2022-05-08 2:13pm

Generated on May 8, 2022

Dataset Split

Train Set 60%
3Images
Valid Set 20%
1Images
Test Set 20%
1Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region

Augmentations

Outputs per training example: 3
Noise: Up to 5% of pixels
Cutout: 3 boxes with 10% size each
helmet
1168 images
RUT
good-bad-warning-unknown
78 images
person
1000 images