Open
Description
🚀 The feature
The ToTensor() function of torchvision.transforms must be able to handle torch Tensors. If it gets a tensor, it must return the same tensor without modification
Motivation, pitch
The function ToTensor can take a NumPy array as input. But if a torch tensor is passed to it, the function raises an error. It will be better if the function can take PyTorch tensors too without raising error.
Alternatives
No response
Additional context
No response