I want to use the tf.with_dependencies function to save the state of my RNNs. For some reason I get the following error.
tf.with_dependencies
There is no such function in the TensorFlow API. Instead you can use with tf.control_dependencies(): and tf.identity() to achieve the intended effect:
with tf.control_dependencies():
tf.identity()
with tf.control_dependencies([expected_output]): result = tf.identity(input_tensor)