walailak

pilldetect

Classification

pilldetect Image Dataset

v1

2024-05-23 9:30pm

Generated on May 23, 2024

Dataset Split

Train Set 31%
825Images
Valid Set 1%
35Images
Test Set 1%
23Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -21% and +21%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels
Cutout: 4 boxes with 4% size each