hansbambel / multidim_conv

PyTorch code for the Paper "Wind speed prediction using multidimensional convolutional neuralnetworks"

Code for the Paper "Wind speed prediction using multidimensional convolutional neuralnetworks" arXiv-Link

Usage

1. Install the necessary packages from the requirements.txt.
2. Specify the training parameters in train.py.
3. Execute train.py.

Training parameters

It is possible to train multiple models after each other by adding them to the list of models_to_test in the train_wind and train_wind_nl functions.

Proposed model

Our proposed model can be found in wind_models.py under the name MultidimConvNetwork. The Multidimensional Convolution Layer can be found in the same file under MultidimConv.

Citation

@inproceedings{trebing2020wind,
  title={Wind speed prediction using multidimensional convolutional neural networks},
  author={Trebing, Kevin and Mehrkanoon, Siamak},
  booktitle={IEEE symposium series on computational intelligence (IEEE-SSCI)},
  pages={713--720},
  year={2020},
  organization={IEEE}
}

multidim_conv's Issues

about fig7

Thank you for your open code. Here is a question. I don't know how to plotted the wind speed prediction for the cities of Eindhoven and Maastricht at each time step, like Figure 7 in your article. If you can take the time to answer it, thank you very much.

Such functions do not allow the output views to be modified inplace

  File "D:\python_project\multidim_conv-master\multidim_conv-master\train.py", line 404, in <module>
    train_wind_nl(folder+data, epochs=150, input_timesteps=6, prediction_timestep=t, dev=dev, earlystopping=20)
  File "D:\python_project\multidim_conv-master\multidim_conv-master\train.py", line 307, in train_wind_nl
    summary(model, (7, input_timesteps, 6), device="cpu")
  File "C:\Users\xinyi\.conda\envs\pytorch\lib\site-packages\torchsummary\torchsummary.py", line 72, in summary
    model(*x)
  File "C:\Users\xinyi\.conda\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\Users\xinyi\.conda\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\python_project\multidim_conv-master\multidim_conv-master\models\wind_models.py", line 93, in forward
    x = F.relu(self.conv1(x))
  File "C:\Users\xinyi\.conda\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\Users\xinyi\.conda\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1568, in _call_impl
    result = forward_call(*args, **kwargs)
  File "D:\python_project\multidim_conv-master\multidim_conv-master\models\attention_augmented_conv.py", line 52, in forward
    flat_q, flat_k, flat_v, q, k, v = self.compute_flat_qkv(x, self.dk, self.dv, self.Nh)
  File "D:\python_project\multidim_conv-master\multidim_conv-master\models\attention_augmented_conv.py", line 79, in compute_flat_qkv
    q *= dkh ** -0.5
RuntimeError: Output 0 of ReshapeAliasBackward0 is a view and is being modified inplace. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one. 

Hello author, I created a new virtual environment in Anaconda and installed the latest version of PyTorch. However, when running the code, it stops and throws an error around 30%. The error code is shown above. I searched on Google and made some improvements to the line of code q *= dkh ** -0.5. Now it doesn't stop at 30% anymore, but it starts from 0 again. I spent a long time trying to figure it out but couldn't. I hope to get your answer on what I should do to run your code.