Computer Vision

Hand Holding Object

Classification

Hand Holding Object Image Dataset

v1

2023-10-19 9:54pm

Generated on Oct 20, 2023

Dataset Split

Train Set 92%
225Images
Valid Set 4%
10Images
Test Set 4%
9Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 412x412

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 44% Maximum Zoom
Rotation: Between -25° and +25°
Shear: ±12° Horizontal, ±12° Vertical
Hue: Between -11° and +11°
Saturation: Between -17% and +17%
Brightness: Between -7% and +7%
Exposure: Between -10% and +10%
Blur: Up to 0.5px
Noise: Up to 1% of pixels