Jace

AI Image Detector

Classification

AI Image Detector Image Dataset

v5

AI Image Detector

Generated on Jan 10, 2024

Dataset Split

Train Set 87%
198Images
Valid Set 8%
19Images
Test Set 4%
10Images

Preprocessing

Resize: Fill (with center crop) in 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Brightness: Between -10% and +10%
Exposure: Between -15% and +15%
Blur: Up to 1.7px