Keras - ValueError when compiling model

I am new to Keras. I want to reproduce the example of imdb in Keras (Backend: Tensorflow) and I get an error when trying to compile the model.

from keras import models
from keras import layers
model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
             loss='binary_crossentropy',
             metrics=['accuracy'])

ValueError: Only call `sigmoid_cross_entropy_with_logits` with named 
arguments (labels=..., logits=..., ...)

Any advice?

Thanks a lot!