Issue Title: Error Encountered: TypeError in grid_sample_gradfix.py

[fader2077]

I encountered an error while running the script using the provided run_script.sh. Below is the traceback of the error:
And this is error

Traceback (most recent call last):
  File "/root/code/iiis508/Desktop/studiogan/NoisyTwins/src/main.py", line 196, in <module>
    loader.load_worker(local_rank=rank,
  File "/root/code/iiis508/Desktop/studiogan/NoisyTwins/src/loader.py", line 366, in load_worker
    gen_acml_loss = worker.train_generator(current_step=step)
  File "/root/code/iiis508/Desktop/studiogan/NoisyTwins/src/worker.py", line 702, in train_generator
    gen_acml_loss.backward()
  File "/opt/conda/lib/python3.10/site-packages/torch/_tensor.py", line 492, in backward
    torch.autograd.backward(
  File "/opt/conda/lib/python3.10/site-packages/torch/autograd/__init__.py", line 251, in backward
    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
  File "/opt/conda/lib/python3.10/site-packages/torch/autograd/function.py", line 288, in apply
    return user_fn(self, *args)
  File "/root/code/iiis508/Desktop/studiogan/NoisyTwins/src/utils/style_ops/grid_sample_gradfix.py", line 52, in backward
    grad_input, grad_grid = _GridSample2dBackward.apply(grad_output, input, grid)
  File "/opt/conda/lib/python3.10/site-packages/torch/autograd/function.py", line 539, in apply
    return super().apply(*args, **kwargs)  # type: ignore[misc]
  File "/root/code/iiis508/Desktop/studiogan/NoisyTwins/src/utils/style_ops/grid_sample_gradfix.py", line 61, in forward
    grad_input, grad_grid = op(grad_output, input, grid, 0, 0, False)
TypeError: 'tuple' object is not callable

Steps to Reproduce:

Execute the script run_script.sh.
Observe the error mentioned above.

Expected Behavior:
The script should run without encountering any errors.

Additional Information:

This error seems to originate from grid_sample_gradfix.py at line 61.
The script is part of the NoisyTwins project.

Any assistance in debugging this issue would be greatly appreciated. Thank you!

[rangwani-harsh]

Hi,

Please tell us which version of PyTorch you are using. I guess it might arise due to a version mismatch.

Can you try with Pytorch 1.13.1?

Thanks
Harsh