In [1]:

    

import numpy as np
from random import shuffle
train_input = ['{0:020b}'.format(i) for i in range(2**20)]


    

In [2]:

    

shuffle(train_input)
train_input = [map(int,i) for i in train_input]


    

In [3]:

    

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


    

In [4]:

    

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)


    

In [5]:

    

NUM_EXAMPLES = 10000
test_input = train_input[NUM_EXAMPLES:]
test_output = train_output[NUM_EXAMPLES:] #everything beyond 10,000
 
train_input = train_input[:NUM_EXAMPLES]
train_output = train_output[:NUM_EXAMPLES] #till 10,000


    

In [6]:

    

print len(train_input[0])
print len(train_output[0])


    

    




20
21

In [7]:

    

import tensorflow as tf


    

In [8]:

    

data = tf.placeholder(tf.float32, [None, 20,1])
target = tf.placeholder(tf.float32, [None, 21])


    

In [9]:

    

num_hidden = 24
cell = tf.nn.rnn_cell.LSTMCell(num_hidden,state_is_tuple=True)

val, state = 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]]))


    

In [10]:

    

prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)


    

In [11]:

    

cross_entropy = -tf.reduce_sum(target * tf.log(tf.clip_by_value(prediction,1e-10,1.0)))


    

In [12]:

    

optimizer = tf.train.AdamOptimizer()
minimize = optimizer.minimize(cross_entropy)


    

    




/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gradients_impl.py:91: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
  "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "

In [13]:

    

mistakes = tf.not_equal(tf.argmax(target, 1), tf.argmax(prediction, 1))
error = tf.reduce_mean(tf.cast(mistakes, tf.float32))


    

In [14]:

    

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


    

    




WARNING:tensorflow:From <ipython-input-14-408081acccf8>:1 in <module>.: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.

In [15]:

    

batch_size = 1000
no_of_batches = int(len(train_input)/batch_size)
epoch =500
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('Epoch {:2d} error {:3.1f}%'.format(i + 1, 100 * incorrect))
# sess.close()


    

    




Epoch 500 error 0.4%

In [16]:

    

test_result = sess.run(prediction,{data: [inp[0]]})


    

In [17]:

    

count =0
for i in inp[0]:
    if i == [1]:
        count += 1
print count


    

    




7

In [18]:

    

test_result.argmax()


    

    
Out[18]:





7

In [ ]: