Unable to run the Run_RNN_model_lite.py script. Index error
ClementJaccarino opened this issue · 0 comments
I have been trying for a couple of weeks to launch your script in order to test a little bit more the result you have with your project.
I have fix all the issues I encounter in the run_feature_cube.py script and I did setup a python environment with the right version of Tensorflow to run the model.
The issues I have now come from an index error the next_batch() function in the datasets_lite.py script and more precisely from this line :
269 - batch_inputs_feature_cubes = self.train_feature_cubes[self.idx:endidx, :, :, :, :]
IndexError: too many indices for array: array is 1-dimensional, but 5 were indexed
The error come from the reading of the file feature_cubes.npz and I am not sure why the array is only a 1 dimensional array when it should be a 5 dimensional array.
I am using Python 3.7.9 and I didn't do any major changes to the run_features_cube.py script.
Do you have any advice for me in order to run you project properly ?