基本例子

Tensorflow 不僅僅是一個深度學習框架。它是以並行和分佈方式執行一般數學運算的通用計算框架。下面描述這樣的一個例子。

線性迴歸

通常使用且計算相當簡單的基本統計示例是將線擬合到資料集。在張量流中這樣做的方法在下面的程式碼和註釋中描述。

（TensorFlow）指令碼的主要步驟是：

1. 宣告佔位符 （x_ph，y_ph）和變數 （W，b）
2. 定義初始化運算子（init）
3. 宣告佔位符和變數的操作（y_pred，loss，train_op）
4. 建立一個會話（sess）
5. 執行初始化運算子（sess.run(init)）
6. 執行一些圖形操作（例如 sess.run([train_op, loss], feed_dict={x_ph: x, y_ph: y})）

圖形構造使用 Python TensorFlow API 完成（也可以使用 C++ TensorFlow API 完成）。執行圖形將呼叫低階 C++例程。

'''
function: create a linear model which try to fit the line 
          y = x + 2 using SGD optimizer to minimize 
          root-mean-square(RMS) loss function

'''
import tensorflow as tf
import numpy as np

# number of epoch
num_epoch = 100

# training data x and label y
x = np.array([0., 1., 2., 3.], dtype=np.float32)
y = np.array([2., 3., 4., 5.], dtype=np.float32)

# convert x and y to 4x1 matrix
x = np.reshape(x, [4, 1])
y = np.reshape(y, [4, 1])

# test set(using a little trick)
x_test = x + 0.5
y_test = y + 0.5

# This part of the script builds the TensorFlow graph using the Python API

# First declare placeholders for input x and label y
# Placeholders are TensorFlow variables requiring to be explicitly fed by some 
# input data
x_ph = tf.placeholder(tf.float32, shape=[None, 1])
y_ph = tf.placeholder(tf.float32, shape=[None, 1])

# Variables (if not specified) will be learnt as the GradientDescentOptimizer
# is run
# Declare weight variable initialized using a truncated_normal law
W = tf.Variable(tf.truncated_normal([1, 1], stddev=0.1))
# Declare bias variable initialized to a constant 0.1
b = tf.Variable(tf.constant(0.1, shape=[1]))

# Initialize variables just declared 
init = tf.initialize_all_variables()

# In this part of the script, we build operators storing operations
# on the previous variables and placeholders.
# model: y = w * x + b
y_pred = x_ph * W + b

# loss function
loss = tf.mul(tf.reduce_mean(tf.square(tf.sub(y_pred, y_ph))), 1. / 2)
# create training graph
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# This part of the script runs the TensorFlow graph (variables and operations
# operators) just built.
with tf.Session() as sess:
    # initialize all the variables by running the initializer operator
    sess.run(init)
    for epoch in xrange(num_epoch):
        # Run sequentially the train_op and loss operators with
        # x_ph and y_ph placeholders fed by variables x and y
        _, loss_val = sess.run([train_op, loss], feed_dict={x_ph: x, y_ph: y})
        print('epoch %d: loss is %.4f' % (epoch, loss_val))

    # see what model do in the test set
    # by evaluating the y_pred operator using the x_test data
    test_val = sess.run(y_pred, feed_dict={x_ph: x_test})
    print('ground truth y is: %s' % y_test.flatten())
    print('predict y is     : %s' % test_val.flatten())