Daekyoung Oh

vision_counting_seg

Instance Segmentation

vision_counting_seg Image Dataset

v2

2023-08-24 2:03pm

Generated on Aug 24, 2023

Dataset Split

Train Set 85%
300Images
Valid Set %
0Images
Test Set 15%
52Images

Preprocessing

No preprocessing steps were applied.

Augmentations

Outputs per training example: 3
Flip: Horizontal
Shear: ±4° Horizontal, ±4° Vertical
Saturation: Between -30% and +30%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 2px