Recurrent Neural Network in TensorFlow

# Import MINST data
import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

import tensorflow as tf
from tensorflow.models.rnn import rnn, rnn_cell
import numpy as np

'''
To classify images using a reccurent neural network, we consider every image row as a sequence of pixels.
Because MNIST image shape is 28*28px, we will then handle 28 sequences of 28 steps for every sample.
'''

# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 128
display_step = 10

# Network Parameters
n_input = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST total classes (0-9 digits)

# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
istate = tf.placeholder("float", [None, 2*n_hidden]) #state & cell => 2x n_hidden
y = tf.placeholder("float", [None, n_classes])

# Define weights
weights = {
    'hidden': tf.Variable(tf.random_normal([n_input, n_hidden])), # Hidden layer weights
    'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
    'hidden': tf.Variable(tf.random_normal([n_hidden])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

def RNN(_X, _istate, _weights, _biases):

    # input shape: (batch_size, n_steps, n_input)
    _X = tf.transpose(_X, [1, 0, 2])  # permute n_steps and batch_size
    # Reshape to prepare input to hidden activation
    _X = tf.reshape(_X, [-1, n_input]) # (n_steps*batch_size, n_input)
    # Linear activation
    _X = tf.matmul(_X, _weights['hidden']) + _biases['hidden']

    # Define a lstm cell with tensorflow
    lstm_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0)
    # Split data because rnn cell needs a list of inputs for the RNN inner loop
    _X = tf.split(0, n_steps, _X) # n_steps * (batch_size, n_hidden)

    # Get lstm cell output
    outputs, states = rnn.rnn(lstm_cell, _X, initial_state=_istate)

    # Linear activation
    # Get inner loop last output
    return tf.matmul(outputs[-1], _weights['out']) + _biases['out']