aaditi

Damage_detection

Instance Segmentation

Damage_detection Image Dataset

v4

2023-12-13 9:40pm

Generated on Dec 13, 2023

Dataset Split

Train Set 88%
7056Images
Valid Set 8%
641Images
Test Set 4%
314Images

Preprocessing

No preprocessing steps were applied.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Grayscale: Apply to 50% of images
Saturation: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Bounding Box: Exposure: Between -25% and +25%