RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [200, 2]], which is output 0 of AsStridedBackward0, is at version 1401; expected version 1400 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

[lsch0lz]

Hi! I'm currently trying to implement CLUE in Python3. I ran into this error when using CLUE for the lsat example (CLUE_pythonclass_wiewing_Tabular_LSAT.ipynb) you provided.

It seems that the backward-pass in clue.py changes the value of a Tensor inplace, which results in the following message.

Did you encounter a similar problem?

Here is the full Traceback:

/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/autograd/__init__.py:266: UserWarning: Error detected in AddmmBackward0. Traceback of forward call that caused the error:
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 2235, in <module>
    main()
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 2217, in main
    globals = debugger.run(setup['file'], None, None, is_module)
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 1527, in run
    return self._exec(is_module, entry_point_fn, module_name, file, globals, locals)
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 1534, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/Users/lukasscholz/repositorys/counterfactuals/examples/test.py", line 210, in <module>
    main()
  File "/Users/lukasscholz/repositorys/counterfactuals/examples/test.py", line 189, in main
    z_vec, x_vec, uncertainty_vec, epistemic_vec, aleatoric_vec, cost_vec, dist_vec = CLUE_explainer.optimise(
  File "/Users/lukasscholz/repositorys/counterfactuals/counterfactual_xai/methods/clue.py", line 191, in optimise
    total_uncertainty, aleatoric_uncertainty, epistemic_uncertainty, x, preds = self.uncertainty_from_z()
  File "/Users/lukasscholz/repositorys/counterfactuals/counterfactual_xai/methods/clue.py", line 124, in uncertainty_from_z
    mu_vec, std_vec = self.BNN.sample_predict(to_BNN, num_samples=0, grad=True)
  File "/Users/lukasscholz/repositorys/counterfactuals/counterfactual_xai/utils/clue/bnn/gaussian_bnn.py", line 134, in sample_predict
    mu, std = self.model(x)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/counterfactual_xai/utils/clue/gaussian_mlp.py", line 27, in forward
    x = self.block(x)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/container.py", line 217, in forward
    input = module(input)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 116, in forward
    return F.linear(input, self.weight, self.bias)
 (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/torch/csrc/autograd/python_anomaly_mode.cpp:118.)
  Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
Traceback (most recent call last):
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/pydevd.py", line 1534, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/Users/lukasscholz/Applications/PyCharm Professional Edition.app/Contents/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/Users/lukasscholz/repositorys/counterfactuals/examples/test.py", line 210, in <module>
    main()
  File "/Users/lukasscholz/repositorys/counterfactuals/examples/test.py", line 189, in main
    z_vec, x_vec, uncertainty_vec, epistemic_vec, aleatoric_vec, cost_vec, dist_vec = CLUE_explainer.optimise(
  File "/Users/lukasscholz/repositorys/counterfactuals/counterfactual_xai/methods/clue.py", line 194, in optimise
    objective.sum(dim=0).backward()  # backpropagate
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/_tensor.py", line 522, in backward
    torch.autograd.backward(
  File "/Users/lukasscholz/repositorys/counterfactuals/venv/lib/python3.10/site-packages/torch/autograd/__init__.py", line 266, in backward
    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [200, 2]], which is output 0 of AsStridedBackward0, is at version 1401; expected version 1400 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!