tensorflow系统学习（1）：如何使用tensorflow

1.tensorflow简单例子

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import os
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)

# To plot pretty figures
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12

# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "images"

def save_fig(fig_id, tight_layout=True):
    path = os.path.join(PROJECT_ROOT_DIR, CHAPTER_ID, "up_and_running_with_tensorflow", fig_id + ".png")
    print("Saving figure", fig_id)
    if tight_layout:
        plt.tight_layout()
    plt.savefig(path, format='png', dpi=300)


#### 1.创Creating and running a graph
reset_graph()
x = tf.Variable(3, name="x")
y = tf.Variable(4, name="y")
f = x*x*y + y + 2
print(f)

# 方法一
sess = tf.Session()
sess.run(x.initializer)
sess.run(y.initializer)
result = sess.run(f)
print(result)
sess.close()

# 方法二
with tf.Session() as sess:
    x.initializer.run()
    y.initializer.run()
    result = f.eval()
print(result)

# 方法三
init = tf.global_variables_initializer()
with tf.Session() as sess:
    init.run()
    result = f.eval()
print(result)


#### 2.Managing graphs
# default
reset_graph()
x1 = tf.Variable(1)
print(x1.graph is tf.get_default_graph())  # True

# managing default
graph = tf.Graph()
with graph.as_default():
    x2 = tf.Variable(2)

print(x2.graph is graph)  # True

print(x2.graph is tf.get_default_graph())  # False


#### 3.Node value life cycle
w = tf.constant(3)
x = w + 2
y = x + 5
z = x * 3

with tf.Session() as sess:  # Below y and z will be executed twice
    print(y.eval())  # 10
    print(z.eval())  # 15

with tf.Session() as sess:  # The following y and z will be executed once
    y_val, z_val = sess.run([y, z])
    print(y_val)  # 10
    print(z_val)  # 15

2.tensorflow线性回归

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import os
import tensorflow as tf
import numpy as np
from sklearn.datasets import fetch_california_housing

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


reset_graph()

housing = fetch_california_housing()
m, n = housing.data.shape
housing_data_plus_bias = np.c_[np.ones((m, 1)), housing.data]

X = tf.constant(housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
XT = tf.transpose(X)
theta = tf.matmul(tf.matmul(tf.matrix_inverse(tf.matmul(XT, X)), XT), y)

with tf.Session() as sess:
    theta_value = theta.eval()
print(theta_value)

纯numpy计算线性回归

import numpy as np

reset_graph()

housing = fetch_california_housing()
m, n = housing.data.shape
housing_data_plus_bias = np.c_[np.ones((m, 1)), housing.data]

X = housing_data_plus_bias
y = housing.target.reshape(-1, 1)
theta_numpy = np.linalg.inv(X.T.dot(X)).dot(X.T).dot(y)

print(theta_numpy)

使用sklearn

from sklearn.linear_model import LinearRegression
from sklearn.datasets import fetch_california_housing
lin_reg = LinearRegression()
housing = fetch_california_housing()
lin_reg.fit(housing.data, housing.target.reshape(-1, 1))

print(np.r_[lin_reg.intercept_.reshape(-1, 1), lin_reg.coef_.T])

手工计算梯度

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import os
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")
gradients = 2 / m * tf.matmul(tf.transpose(X), error)
training_op = tf.assign(theta, theta - learning_rate * gradients)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())
        sess.run(training_op)

    best_theta = theta.eval()

使用autodiff

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")

gradients = tf.gradients(mse, [theta])[0]

training_op = tf.assign(theta, theta - learning_rate * gradients)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())
        sess.run(training_op)

    best_theta = theta.eval()

print("Best theta:")
print(best_theta)

对某个函数求偏导

原本函数：

def my_func(a, b):
    z = 0
    for i in range(100):
        z = a * np.cos(z + i) + z * np.sin(b - i)
    return z

print(my_func(0.2, 0.3))  # -0.21253923284754914

使用tensorflow：

reset_graph()

a = tf.Variable(0.2, name="a")
b = tf.Variable(0.3, name="b")
z = tf.constant(0.0, name="z0")
for i in range(100):
    z = a * tf.cos(z + i) + z * tf.sin(b - i)

grads = tf.gradients(z, [a, b])
init = tf.global_variables_initializer()

with tf.Session() as sess:
    init.run()
    print(z.eval())  # -0.21253741
    print(sess.run(grads))  # [-1.1388495, 0.19671397]

使用优化器：

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")

optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(mse)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())
        sess.run(training_op)

    best_theta = theta.eval()

print("Best theta:")
print(best_theta)

使用momentum优化器

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")

optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate, momentum=0.9)

training_op = optimizer.minimize(mse)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())
        sess.run(training_op)

    best_theta = theta.eval()

print("Best theta:")
print(best_theta)

使用小批次梯度下降：

占位符节点案例：

reset_graph()

A = tf.placeholder(tf.float32, shape=(None, 3))
B = A + 5
with tf.Session() as sess:
    B_val_1 = B.eval(feed_dict={A: [[1, 2, 3]]})
    B_val_2 = B.eval(feed_dict={A: [[4, 5, 6], [7, 8, 9]]})

print(B_val_1)  # [[6. 7. 8.]]
print(B_val_2)  # [[ 9. 10. 11.][12. 13. 14.]]

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time:       2019/11/30 16:52
# @Author:     weiz
# @File:       09_up_and_running_with_tensorflow.py
# @Description:

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import tensorflow as tf

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)


from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.placeholder(tf.float32, shape=(None, n + 1), name="X")
y = tf.placeholder(tf.float32, shape=(None, 1), name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(mse)

init = tf.global_variables_initializer()
n_epochs = 10
batch_size = 100
n_batches = int(np.ceil(m / batch_size))

def fetch_batch(epoch, batch_index, batch_size):
    np.random.seed(epoch * n_batches + batch_index)  # not shown in the book
    indices = np.random.randint(m, size=batch_size)  # not shown
    X_batch = scaled_housing_data_plus_bias[indices] # not shown
    y_batch = housing.target.reshape(-1, 1)[indices] # not shown
    return X_batch, y_batch

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        for batch_index in range(n_batches):
            X_batch, y_batch = fetch_batch(epoch, batch_index, batch_size)
            sess.run(training_op, feed_dict={X: X_batch, y: y_batch})

    best_theta = theta.eval()

print(best_theta)