vmo31 innopolis

innopolis dog pose

Keypoint Detection

innopolis dog pose Image Dataset

v1

first xyeta

Generated on Jun 7, 2024

Dataset Split

Train Set 85%
249Images
Valid Set 10%
30Images
Test Set 5%
15Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Grayscale: Apply to 20% of images
Brightness: Between -24% and +24%