The following problems occurred when running train.py. Would you please help me? Thank you very much.

[zhp66]

Traceback (most recent call last):
File "C:/Users/58413/Desktop/ODL-master/ODL-master/src/train.py", line 61, in
model.compile(optimizer=optim, loss = ['mse','mse','mse'], hedge = True, loss_weights = [1.0/3]*3, metrics =['accuracy'])
File "C:\Anaconda3\lib\site-packages\keras\engine\training.py", line 684, in compile
total_loss = K.sum(K.dot(self.holder, self.metrics_tensors))
File "C:\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 790, in dot
if ndim(x) is not None and (ndim(x) > 2 or ndim(y) > 2):
File "C:\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 396, in ndim
dims = x.get_shape()._dims
AttributeError: 'list' object has no attribute 'get_shape'

[phquang]

Hi, it seems like you are using Tensorflow backend while our implementation only supports Theano backend. Moreover, please check and use the correct dependencies versions.

[zhp66]

Thank you very much for your reply. I have another question: can onn solve the regression problem?