nk950357@gmail.com

lab

Instance Segmentation

lab Image Dataset

v10

2022-11-23 5:24pm

Generated on Nov 23, 2022

Dataset Split

Train Set 96%
792Images
Valid Set 4%
29Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 550x550
Auto-Adjust Contrast: Using Contrast Stretching
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -10° and +10°
Shear: ±12° Horizontal, ±6° Vertical
Hue: Between -31° and +31°
Saturation: Between -6% and +6%
Brightness: Between -30% and +30%
Blur: Up to 1.5px
Noise: Up to 4% of pixels
Cutout: 7 boxes with 3% size each
Bounding Box: Exposure: Between -13% and +13%