YOLOV7

Step2-v1_2-sand-illu-2-beixinyao

Instance Segmentation

Step2-v1_2-sand-illu-2-beixinyao Image Dataset

v1

Step2_v1.2

Generated on Jan 28, 2023

Dataset Split

Train Set 94%
3059Images
Valid Set 4%
125Images
Test Set 2%
63Images

Preprocessing

Resize: Stretch to 1280x1280

Augmentations

Outputs per training example: 7
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Shear: ±15° Horizontal, ±15° Vertical
Noise: Up to 5% of pixels
Cutout: 5 boxes with 10% size each