kiwidetectionyolov3

kiwidetection

Object Detection

kiwidetection Image Dataset

v1

2022-05-07 5:22pm

Generated on May 7, 2022

Popular Download Formats

Dataset Split

Train Set 96%
804Images
Valid Set 4%
30Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 42% Maximum Zoom
Shear: ±30° Horizontal, ±30° Vertical
Grayscale: Apply to 59% of images
Hue: Between -101° and +101°
Saturation: Between -60% and +60%
Brightness: Between -41% and +41%
Exposure: Between -10% and +10%
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Brightness: Between -70% and +70%
Bounding Box: Blur: Up to 20px
Bounding Box: Noise: Up to 25% of pixels