Tiling layer causing incorrect graph creation in Pytorch

[sandeepnmenon]

While trying to train the vpgnet model with the Tiling layer, I am getting the following error

    loss.backward()
  File "/home/SandeepMenon/venv-e3d/lib/python3.6/site-packages/torch/tensor.py", line 221, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/home/SandeepMenon/venv-e3d/lib/python3.6/site-packages/torch/autograd/__init__.py", line 132, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: Trying to backward through the graph a second time, but the saved intermediate results have already been freed. Specify retain_graph=True when calling backward the first time.

I suspect this to be the Tiling layer issue, because when I remove the tiling layer (and resize the ground truth accordingly), the model trains without errors.