To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor). #3
Description
Warning to resolve in beexai/evaluate/metrics/infidelity.py:42 and beexai/evaluate/metrics/sensitivity.py:51:
To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).