wwu-mmll / mccqrnn_docker

GNU Affero General Public License v3.0
3 stars 2 forks source link

IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed #3

Closed RDoerfel closed 1 year ago

RDoerfel commented 1 year ago

Hello, now where docker is up and running, I have another issue. It seems like some dimensions are not matching.

I did the following:

  1. Runn the standard segmentation pipeline of Cat12 with he specified version
  2. Take the gray matter segmented image (mwp1001.nii)
  3. run docker with mounting and pointing towards the csv file.

Here is the complete log:

Traceback (most recent call last):
  File "entrypoint.py", line 34, in <module>
    main()
  File "entrypoint.py", line 26, in main
    y = my_pipe.predict(X)
  File "/usr/local/envs/mccqrnn/lib/python3.7/site-packages/photonai/base/photon_pipeline.py", line 402, in predict
    y_pred = self._final_estimator.predict(X, **kwargs)
  File "/usr/local/envs/mccqrnn/lib/python3.7/site-packages/photonai/base/photon_elements.py", line 392, in predict
    return self.__predict(X, **kwargs)
  File "/usr/local/envs/mccqrnn/lib/python3.7/site-packages/photonai/base/photon_elements.py", line 379, in __predict
    return self.adjusted_predict_call(self.base_element.predict, X, **kwargs)
  File "/usr/local/envs/mccqrnn/lib/python3.7/site-packages/photonai/base/photon_elements.py", line 530, in adjusted_predict_call
    return delegate(X)
  File "photon_best_model/MCCQRNN_Regressor.py", line 127, in predict
  File "photon_best_model/MCCQRNN_Regressor.py", line 155, in fill_val_dict
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed
jernsting commented 1 year ago

Could you please try using at least two images or the same image twice? I remember that predictions for only one subject are problematic.

RDoerfel commented 1 year ago

Ok that worked! Thanks :)