case4

case4

Object Detection

case4 Image Dataset

v3

full_150size

Generated on May 4, 2023

Popular Download Formats

Dataset Split

Train Set 87%
14217Images
Valid Set 8%
1346Images
Test Set 4%
691Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 150x150

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -20° and +20°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Saturation: Between -64% and +64%
Brightness: Between -46% and +46%
Exposure: Between -21% and +21%
Blur: Up to 3.25px
Noise: Up to 15% of pixels
Cutout: 4 boxes with 25% size each