TensorFlow基础系列（线性回归）

线性回归

比较基础的模型，这边不多介绍，这里主要将tensorflow的基本编程模式

TensorFlow的一般模式是，先构建图（也就是你的模型），然后使用sess往图里注入数据。迭代训练图中的各项参数。

废话不多说，我们直接看带session的代码。

A linear regression learning algorithm example using TensorFlow library.
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''

from __future__ import print_function

import tensorflow as tf
import numpy
import matplotlib.pyplot as plt
rng = numpy.random

# 超参数的设置
learning_rate = 0.01
training_epochs = 1000
display_step = 50

# 训练数据的准备
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
                         7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
                         2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape[0]


#图的构建
# tf Graph Input （在构建图的时候，图的输入都是占位的）
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# Construct a linear model （模型的核心）
pred = tf.add(tf.multiply(X, W), b)

# Mean squared error  （损失函数）
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
#  Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
#优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()



#这里开始注入数据
# Start training
with tf.Session() as sess:

    # Run the initializer
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
                "W=", sess.run(W), "b=", sess.run(b))

    print("Optimization Finished!")
    training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
    print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

    # Graphic display
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()

    # Testing example, as requested (Issue #2)
    test_X = numpy.asarray([6.83, 4.668, 8.9, 7.91, 5.7, 8.7, 3.1, 2.1])
    test_Y = numpy.asarray([1.84, 2.273, 3.2, 2.831, 2.92, 3.24, 1.35, 1.03])

    print("Testing... (Mean square loss Comparison)")
    testing_cost = sess.run(
        tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * test_X.shape[0]),
        feed_dict={X: test_X, Y: test_Y})  # same function as cost above
    print("Testing cost=", testing_cost)
    print("Absolute mean square loss difference:", abs(
        training_cost - testing_cost))

    plt.plot(test_X, test_Y, 'bo', label='Testing data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()

机器学习模型一般都分三部分，模型构建，损失函数，然后优化函数。上面一个简单的线性模型三部分也很清晰地给出来了。

eager模式的线性回归

这是tf新加入的特性，我们之前的博客也介绍过了。这里让我们看看使用eager模式能让我们线性回归少写多少代码。

''' Linear Regression with Eager API.
A linear regression learning algorithm example using TensorFlow's Eager API.
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''
from __future__ import absolute_import, division, print_function

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf

# Set Eager API
#使用前要先设置一下，让程序知道你要走这个模式
tf.enable_eager_execution()
tfe = tf.contrib.eager

# Training Data
train_X = [3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,
           7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1]
train_Y = [1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,
           2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3]
n_samples = len(train_X)

# Parameters
learning_rate = 0.01
display_step = 100
num_steps = 1000


# Weight and Bias
W = tfe.Variable(np.random.randn())
b = tfe.Variable(np.random.randn())


# Linear regression (Wx + b)
def linear_regression(inputs):
    return inputs * W + b


# Mean square error
##接受模型，输入和lable，计算损失
def mean_square_fn(model_fn, inputs, labels):
    return tf.reduce_sum(tf.pow(model_fn(inputs) - labels, 2)) / (2 * n_samples)


# SGD Optimizer
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
# Compute gradients

##接受模型的损失函数
grad = tfe.implicit_gradients(mean_square_fn)

# Initial cost, before optimizing
print("Initial cost= {:.9f}".format(
    mean_square_fn(linear_regression, train_X, train_Y)),
    "W=", W.numpy(), "b=", b.numpy())

# Training
for step in range(num_steps):
    
    ##这里接受grad，损失函数（模型，输入，label），主要就是这里训练
    optimizer.apply_gradients(grad(linear_regression, train_X, train_Y))

    if (step + 1) % display_step == 0 or step == 0:
        print("Epoch:", '%04d' % (step + 1), "cost=",
              "{:.9f}".format(mean_square_fn(linear_regression, train_X, train_Y)),
              "W=", W.numpy(), "b=", b.numpy())

# Graphic display
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.plot(train_X, np.array(W * train_X + b), label='Fitted line')
plt.legend()
plt.show()

这里的代码显得有点大不相同，写久了原来的tensorflow突然切换过来还是很不习惯的。这里的编程模式很像estimator

这个代码一层套一层，显得有点绕，其实本质和之前还是一样的。除了不用session，数据还是在所有东西定义好，输入的。这就是tf的基本特征。