original_to_model

lightning_pose.data.utils.original_to_model(keypoints: Float[Tensor, 'batch num_keypoints 2'], bbox: Float[Tensor, 'batch 4'], model_width: float, model_height: float) → Float[Tensor, 'batch num_keypoints 2']

Convert keypoints from original image coordinates to model input coordinates.

This combines the transformations: 1. original → bbox: subtract offset, divide by bbox dimensions 2. bbox → model: multiply by model dimensions

bbox format: [x, y, h, w] where x,y is top-left corner