Omar Alnasier

d5

Instance Segmentation

d5 Image Dataset

v2

2022-11-21 12:38pm

Generated on Nov 21, 2022

Dataset Split

Train Set 97%
1962Images
Valid Set 3%
57Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 4 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Shear: ±32° Horizontal, ±19° Vertical
Grayscale: Apply to 25% of images
Brightness: Between -37% and +37%