'NoneType' object is not subscriptable

[Leila-sd]

Hi,
help me to rectify this error
Traceback (most recent call last):
File "main.py", line 73, in
m = Model(input=[x, x_maps], output=sam_resnet([x, x_maps]))
File "\sam-master\models.py", line 136, in sam_resnet
nb_cols=3, nb_rows=3)(att_convlstm)
File "\sam-master\keras\engine\base_layer.py", line 457, in call
output = self.call(inputs, **kwargs)
File "\sam-master\attentive_convlstm.py", line 154, in call
input_length=input_shape[1])
File "\sam-master\keras\backend\theano_backend.py", line 1591, in rnn
go_backwards=go_backwards)
File "\Anaconda3\lib\site-packages\theano\scan_module\scan.py", line 773, in scan
condition, outputs, updates = scan_utils.get_updates_and_outputs(fn(*args))
File "\sam-master\keras\backend\theano_backend.py", line 1575, in _step
outputs, new_states = step_function(inputs, states)
File "\sam-master\attentive_convlstm.py", line 123, in step
a = K.reshape(K.softmax(K.batch_flatten(e)), (x_shape[0], 1, x_shape[2], x_shape[3]))
File "\sam-master\keras\backend\theano_backend.py", line 1101, in batch_flatten
if None in x._keras_shape[1:]:
TypeError: 'NoneType' object is not subscriptable
thanks

[Leila-sd]

my keras version 1.1.0, theano version 0.9.0

[marcellacornia]

Our code is compatible with Python 2.7, Keras 1.1.0 and Theano 0.9.0. Please also check your keras.json file (see the README for more details).