xxxxxxxxxx
# Try changing the loss in your model.fit from:
loss="categorical_crossentropy"
#to
loss="binary_crossentropy"
'''
I Had the SAME problem, but this worked for me.
The thing is that I have a binary classification model, with only
1 output node, not a multi-classification model with multiple output
nodes, so loss="binary_crossentropy" is the appropriate loss function
in this case.
'''