nk950357@gmail.com

eclatorq3

Object Detection

eclatorq3 Image Dataset

v12

2024-02-16 10:51pm

Generated on Feb 16, 2024

Popular Download Formats

Dataset Split

Train Set 89%
8142Images
Valid Set 8%
728Images
Test Set 3%
292Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Filter Null: Do not filter any null images.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 11% Maximum Zoom
Rotation: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -32% and +32%
Exposure: Between -20% and +20%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Cutout: 9 boxes with 3% size each
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Exposure: Between -6% and +6%
Bounding Box: Noise: Up to 3% of pixels