Same (?) neural network architecture in Tensorflow and Keras produces different accuracy on the same data

python-3.x tensorflow neural-network deep-learning keras

There is an important difference between Keras and TensorFlow regarding dropout:

In TensorFlow, the argument keep_prob of tf.nn.dropout sets the probability of keeping a unit.
In Keras, the argument rate of keras.layers.Dropout sets the probability of dropping a unit.

In your implementation you're setting the same value to both arguments. You should ensure that keep_prob = 1 - rate.

CodeHunter