Dataset Versions

v3

medaka_pose_v3

Generated on Sep 2, 2024

Dataset Split

Train Set 88%
624Images
Valid Set 9%
61Images
Test Set 4%
27Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied

Augmentations

Outputs per training example: 3
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Blur: Up to 2.5px
Bounding Box: Brightness: Between -20% and +20%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 2.5px