train model to count number of 1's in a sequence of 20 time steps, based on https://gist.github.com/monikkinom/e97d518fe02a79177b081c028a83ec1c

seq1a.py

from keras.models import Sequential
from keras.layers import LSTM, Dense, Activation
import numpy as np
from random import shuffle

#based on: https://gist.github.com/monikkinom/e97d518fe02a79177b081c028a83ec1c
#train model to count number of 1's in a sequence of 20 time steps


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]



model = Sequential()
model.add(LSTM(24, input_shape=(20,1)))
model.add(Dense(21))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

model.fit(np.asarray(train_input), np.asarray(train_output), epochs=1000, batch_size=128)


#loss_and_metrics = model.evaluate(test_input, test_output)

print model.predict(np.asarray([[[1],[0],[0],[1],[1],[0],[1],[1],[1],[0],[1],[0],[0],[1],[1],[0],[1],[1],[1],[0]]]))