Tensorflow RNN-LSTM implementation to count number of set bits in a binary string

rnn-lstm.py

#Source code with the blog post at http://monik.in/a-noobs-guide-to-implementing-rnn-lstm-using-tensorflow/
import numpy as np
import random
from random import shuffle
import tensorflow as tf

# from tensorflow.models.rnn import rnn_cell
# from tensorflow.models.rnn import rnn

NUM_EXAMPLES = 10000

train_input = ['{0:020b}'.format(i) for i in range(2**20)]
shuffle(train_input)
train_input = [map(int,i) for i in train_input]
ti  = []
for i in train_input:
    temp_list = []
    for j in i:
            temp_list.append([j])
    ti.append(np.array(temp_list))
train_input = ti

train_output = []
for i in train_input:
    count = 0
    for j in i:
        if j[0] == 1:
            count+=1
    temp_list = ([0]*21)
    temp_list[count]=1
    train_output.append(temp_list)

test_input = train_input[NUM_EXAMPLES:]
test_output = train_output[NUM_EXAMPLES:]
train_input = train_input[:NUM_EXAMPLES]
train_output = train_output[:NUM_EXAMPLES]

print "test and training data loaded"


data = tf.placeholder(tf.float32, [None, 20,1]) #Number of examples, number of input, dimension of each input
target = tf.placeholder(tf.float32, [None, 21])
num_hidden = 24
cell = tf.nn.rnn_cell.LSTMCell(num_hidden,state_is_tuple=True)
val, _ = tf.nn.dynamic_rnn(cell, data, dtype=tf.float32)
val = tf.transpose(val, [1, 0, 2])
last = tf.gather(val, int(val.get_shape()[0]) - 1)
weight = tf.Variable(tf.truncated_normal([num_hidden, int(target.get_shape()[1])]))
bias = tf.Variable(tf.constant(0.1, shape=[target.get_shape()[1]]))
prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)
cross_entropy = -tf.reduce_sum(target * tf.log(tf.clip_by_value(prediction,1e-10,1.0)))
optimizer = tf.train.AdamOptimizer()
minimize = optimizer.minimize(cross_entropy)
mistakes = tf.not_equal(tf.argmax(target, 1), tf.argmax(prediction, 1))
error = tf.reduce_mean(tf.cast(mistakes, tf.float32))

init_op = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init_op)

batch_size = 1000
no_of_batches = int(len(train_input)) / batch_size
epoch = 5000
for i in range(epoch):
    ptr = 0
    for j in range(no_of_batches):
        inp, out = train_input[ptr:ptr+batch_size], train_output[ptr:ptr+batch_size]
        ptr+=batch_size
        sess.run(minimize,{data: inp, target: out})
    print "Epoch ",str(i)
incorrect = sess.run(error,{data: test_input, target: test_output})
print sess.run(prediction,{data: [[[1],[0],[0],[1],[1],[0],[1],[1],[1],[0],[1],[0],[0],[1],[1],[0],[1],[1],[1],[0]]]})
print('Epoch {:2d} error {:3.1f}%'.format(i + 1, 100 * incorrect))
sess.close()

Can you write a Lstm to learn an Sin Wave Please, thanks!

I've added the use of tensorboard and works in TF 1.3r2 and Python 3.6

@franciscogmm The index of the largest value of the output is the guess of how many 1's there are, so if there are three 1's, then the perfect output would be [0,0,0,1 ... ] because there aren't 0 1's, there aren't 1 1's, there aren't 2 1's, but there are 3 1's.

Hi, I tried this with TF1.5, then I got an error for the dimension of the first placeholder

Then I checked the code again and change line62 to no_of_batches = int(len(train_input) / batch_size) and now it works.

@franciscogmm it is the name collision. You need to specify different variable scopes for the LSTM cells.

Hi, i got this error when i run this code .please notify me how can i correct this one.
File "", line 66
print sess.run(prediction,{data: [[[1],[0],[0],[1],[1],[0],[1],[1],[1],[0],[1],[0],[0],[1],[1],[0],[1],[1],[1],[0]]]})
^
SyntaxError: invalid syntax