教你从零开始在 TensorFlow 上搭建 RNN（完整代码）！

RNN 是什么?

RNN 处理系列数据的过程图解

设置

1. 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
echo_step = 3
batch_size = 5
num_batches = total_series_length//batch_size//truncated_backprop_length


生成数据

1. 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)


创建计算图

TensorFlow 的工作方式会首先创建一个计算图，来确认哪些操作需要完成。计算图的输入和输出一般是多维阵列，即张量（tensor）。计算图或其中一部分，将被迭代执行。这既可以在 CPU、GPU，也可在远程服务器上执行。

变量和 placeholder

1. 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])


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)    

Unpacking

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


Forward pass

1. # 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

states_series.append(next_state)
current_state = next_state


计算损失

1. 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)    

训练可视化

1. 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)
plt.cla()
plt.axis([0, truncated_backprop_length, 0, 2])
left_offset = range(truncated_backprop_length)
plt.bar(left_offset, batchX[batch_series_idx, :], width=1, color="blue")
plt.bar(left_offset, batchY[batch_series_idx, :] * 0.5, width=1, color="red")
plt.bar(left_offset, single_output_series * 0.3, width=1, color="green")

plt.draw()
plt.pause(0.0001)


运行训练环节

1. 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))

print("New data, epoch", epoch_idx)

for batch_idx in range(num_batches):
start_idx = batch_idx * truncated_backprop_length
end_idx = start_idx + truncated_backprop_length

batchX = x[:,start_idx:end_idx]
batchY = y[:,start_idx:end_idx]

_total_loss, _train_step, _current_state, _predictions_series = sess.run(
[total_loss, train_step, current_state, predictions_series],
feed_dict={
batchX_placeholder:batchX,
batchY_placeholder:batchY,
init_state:_current_state
})

loss_list.append(_total_loss)

if batch_idx%100 == 0:
print("Step",batch_idx, "Loss", _total_loss)
plot(loss_list, _predictions_series, batchX, batchY)

plt.ioff()
plt.show()    

整个系统

1. 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
echo_step = 3
batch_size = 5
num_batches = total_series_length//batch_size//truncated_backprop_length

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)

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])

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)

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

# 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

states_series.append(next_state)
current_state = next_state

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)

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)
plt.cla()
plt.axis([0, truncated_backprop_length, 0, 2])
left_offset = range(truncated_backprop_length)
plt.bar(left_offset, batchX[batch_series_idx, :], width=1, color="blue")
plt.bar(left_offset, batchY[batch_series_idx, :] * 0.5, width=1, color="red")
plt.bar(left_offset, single_output_series * 0.3, width=1, color="green")

plt.draw()
plt.pause(0.0001)

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))

print("New data, epoch", epoch_idx)

for batch_idx in range(num_batches):
start_idx = batch_idx * truncated_backprop_length
end_idx = start_idx + truncated_backprop_length

batchX = x[:,start_idx:end_idx]
batchY = y[:,start_idx:end_idx]

_total_loss, _train_step, _current_state, _predictions_series = sess.run(
[total_loss, train_step, current_state, predictions_series],
feed_dict={
batchX_placeholder:batchX,
batchY_placeholder:batchY,
init_state:_current_state
})

loss_list.append(_total_loss)

if batch_idx%100 == 0:
print("Step",batch_idx, "Loss", _total_loss)
plot(loss_list, _predictions_series, batchX, batchY)

plt.ioff()
plt.show()   

|
9月前
|

【tensorflow】连续输入的神经网络模型训练代码
【tensorflow】连续输入的神经网络模型训练代码
57 0
|
2月前
|

TensorFlow、Keras 和 Python 构建神经网络分析鸢尾花iris数据集|代码数据分享
TensorFlow、Keras 和 Python 构建神经网络分析鸢尾花iris数据集|代码数据分享
99 0
|
2月前
|

【TensorFlow】TF介绍及代码实践
【4月更文挑战第1天】TF简介及代码示例学习
45 0
|
9月前
|

|
2月前
|

79 2
|
2月前
|

55 2
|
2月前
|

458 0
|
2月前
|

【Tensorflow+自然语言处理+RNN】实现中文译英文的智能聊天机器人实战（附源码和数据集 超详细）
【Tensorflow+自然语言处理+RNN】实现中文译英文的智能聊天机器人实战（附源码和数据集 超详细）
57 1
|
8月前
|

190 2
|
8月前
|

keras tensorflow 搭建CNN-LSTM神经网络的住宅用电量预测 完整代码数据
keras tensorflow 搭建CNN-LSTM神经网络的住宅用电量预测 完整代码数据
74 0