upsample

lightning_pose.models.heads.heatmap.upsample(inputs: Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints', 'heatmap_height', 'heatmap_width'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints', 'two_x_heatmap_height', 'two_x_heatmap_width',), 'cls_name': 'TensorType'}]

Upsample batch of heatmaps by a factor of two using interpolation (no learned weights).

This is a copy of kornia’s pyrup function but with better defaults.