Hands-On Deep Learning Algorithms with Python

Defining placeholders

Now, we will define the TensorFlow placeholders:

1. The placeholders for the input and output is defined as:

inputs = tf.placeholder(shape=[None, vocab_size],dtype=tf.float32, name="inputs")targets = tf.placeholder(shape=[None, vocab_size], dtype=tf.float32, name="targets")

2. Define the placeholder for the initial hidden state:

init_state = tf.placeholder(shape=[1, hidden_size], dtype=tf.float32, name="state")

3. Define an initializer for initializing the weights of the RNN:

initializer = tf.random_normal_initializer(stddev=0.1)