3h4

from __future__ import print_function
import matplotlib
import matplotlib.pyplot as plt
import tensorflow as tf
import time

def get_times(maximum_time):

    device_times = {
        "/gpu:0":[],

3h4

from __future__ import print_function, division
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

num_epochs = 100
total_series_length = 50000
truncated_backprop_length = 15
state_size = 4
num_classes = 2

3h4

def generateData():
    x = np.array(np.random.choice(2, total_series_length, p=[0.5, 0.5]))
    y = np.roll(x, echo_step)
    y[0:echo_step] = 0

    x = x.reshape((batch_size, -1))  # The first index changing slowest, subseries as rows
    y = y.reshape((batch_size, -1))

    return (x, y)

3h4

batchX_placeholder = tf.placeholder(tf.float32, [batch_size, truncated_backprop_length])
batchY_placeholder = tf.placeholder(tf.int32, [batch_size, truncated_backprop_length])

init_state = tf.placeholder(tf.float32, [batch_size, state_size])

3h4

W = tf.Variable(np.random.rand(state_size+1, state_size), dtype=tf.float32)
b = tf.Variable(np.zeros((1,state_size)), dtype=tf.float32)

W2 = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b2 = tf.Variable(np.zeros((1,num_classes)), dtype=tf.float32)

3h4

# Unpack columns
inputs_series = tf.unpack(batchX_placeholder, axis=1)
labels_series = tf.unpack(batchY_placeholder, axis=1)

3h4

# Forward pass
current_state = init_state
states_series = []
for current_input in inputs_series:
    current_input = tf.reshape(current_input, [batch_size, 1])
    input_and_state_concatenated = tf.concat(1, [current_input, current_state])  # Increasing number of columns

    next_state = tf.tanh(tf.matmul(input_and_state_concatenated, W) + b)  # Broadcasted addition
    states_series.append(next_state)
    current_state = next_state

3h4

logits_series = [tf.matmul(state, W2) + b2 for state in states_series] #Broadcasted addition
predictions_series = [tf.nn.softmax(logits) for logits in logits_series]

losses = [tf.nn.sparse_softmax_cross_entropy_with_logits(logits, labels) for logits, labels in zip(logits_series,labels_series)]
total_loss = tf.reduce_mean(losses)

train_step = tf.train.AdagradOptimizer(0.3).minimize(total_loss)

3h4

def plot(loss_list, predictions_series, batchX, batchY):
    plt.subplot(2, 3, 1)
    plt.cla()
    plt.plot(loss_list)

    for batch_series_idx in range(5):
        one_hot_output_series = np.array(predictions_series)[:, batch_series_idx, :]
        single_output_series = np.array([(1 if out[0] < 0.5 else 0) for out in one_hot_output_series])

        plt.subplot(2, 3, batch_series_idx + 2)

3h4

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    plt.ion()
    plt.figure()
    plt.show()
    loss_list = []

    for epoch_idx in range(num_epochs):
        x,y = generateData()
        _current_state = np.zeros((batch_size, state_size))