Tensorflow快餐教程(1) - 30行代码搞定手写识别

1. 云栖社区>
2. 博客列表>
3. 正文

## Tensorflow快餐教程(1) - 30行代码搞定手写识别

lusing 2018-04-16 19:36:55 浏览1447 评论1

## Tensorflow安装速成教程

### Linux平台安装tensorflow

sudo apt install python3
sudo apt install python3-pip

pip3 install tensorflow --upgrade

### MacOS安装tensorflow

brew install python3

pip3 install tensorflow --upgrade

### Windows平台安装Tensorflow

Windows平台上建议通过Anaconda来安装tensorflow，下载地址在：https://www.anaconda.com/download/#windows

conda create -n tensorflow pip
activate tensorflow
pip install --ignore-installed --upgrade tensorflow

import tensorflow as tf
a = tf.constant(1)
b = tf.constant(2)

c = a * b

sess = tf.Session()

print(sess.run(c))

Tensorflow顾名思义，是一些Tensor张量的流组成的运算。

Tensor("mul_1:0", shape=(), dtype=int32)

## 入门捷径：线性回归

tf.multiply(X, w)

import tensorflow as tf
import numpy as np

trX = np.linspace(-1, 1, 101)
trY = 2 * trX + np.random.randn(*trX.shape) * 0.33 # 创建一些线性值附近的随机值

X = tf.placeholder("float")
Y = tf.placeholder("float")

def model(X, w):
return tf.multiply(X, w) # X*w线性求值，非常简单

w = tf.Variable(0.0, name="weights")
y_model = model(X, w)

cost = tf.square(Y - y_model) # 用平方误差做为优化目标

train_op = tf.train.GradientDescentOptimizer(0.01).minimize(cost) # 梯度下降优化

# 开始创建Session干活！
with tf.Session() as sess:
# 首先需要初始化全局变量，这是Tensorflow的要求
tf.global_variables_initializer().run()

for i in range(100):
for (x, y) in zip(trX, trY):
sess.run(train_op, feed_dict={X: x, Y: y})

print(sess.run(w)) 

## 多种方式搞定手写识别

### 线性模型：logistic回归

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w):
return tf.matmul(X, w) # 模型还是矩阵乘法

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

w = init_weights([784, 10])
py_x = model(X, w)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # 计算误差
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct optimizer
predict_op = tf.argmax(py_x, 1)

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

for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})
print(i, np.mean(np.argmax(teY, axis=1) ==
sess.run(predict_op, feed_dict={X: teX})))

### 无脑的浅层神经网络

    h = tf.nn.sigmoid(tf.matmul(X, w_h))
return tf.matmul(h, w_o) 

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

# 所有连接随机生成权值
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w_h, w_o):
h = tf.nn.sigmoid(tf.matmul(X, w_h))
return tf.matmul(h, w_o)

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

w_h = init_weights([784, 625])
w_o = init_weights([625, 10])

py_x = model(X, w_h, w_o)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # 计算误差损失
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer
predict_op = tf.argmax(py_x, 1)

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

for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})
print(i, np.mean(np.argmax(teY, axis=1) ==
sess.run(predict_op, feed_dict={X: teX})))

### 深度学习时代的方案 - ReLU和Dropout显神通

    X = tf.nn.dropout(X, p_keep_input)
h = tf.nn.relu(tf.matmul(X, w_h))

h = tf.nn.dropout(h, p_keep_hidden)
h2 = tf.nn.relu(tf.matmul(h, w_h2))

h2 = tf.nn.dropout(h2, p_keep_hidden)

return tf.matmul(h2, w_o)

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w_h, w_h2, w_o, p_keep_input, p_keep_hidden):
X = tf.nn.dropout(X, p_keep_input)
h = tf.nn.relu(tf.matmul(X, w_h))

h = tf.nn.dropout(h, p_keep_hidden)
h2 = tf.nn.relu(tf.matmul(h, w_h2))

h2 = tf.nn.dropout(h2, p_keep_hidden)

return tf.matmul(h2, w_o)

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

w_h = init_weights([784, 625])
w_h2 = init_weights([625, 625])
w_o = init_weights([625, 10])

p_keep_input = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w_h, w_h2, w_o, p_keep_input, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

with tf.Session() as sess:
# you need to initialize all variables
tf.global_variables_initializer().run()

for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
p_keep_input: 0.8, p_keep_hidden: 0.5})
print(i, np.mean(np.argmax(teY, axis=1) ==
sess.run(predict_op, feed_dict={X: teX,
p_keep_input: 1.0,
p_keep_hidden: 1.0})))

### 卷积神经网络出场

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

batch_size = 128
test_size = 256

def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):
l1a = tf.nn.relu(tf.nn.conv2d(X, w,                       # l1a shape=(?, 28, 28, 32)
strides=[1, 1, 1, 1], padding='SAME'))
l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],              # l1 shape=(?, 14, 14, 32)
strides=[1, 2, 2, 1], padding='SAME')
l1 = tf.nn.dropout(l1, p_keep_conv)

l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,                     # l2a shape=(?, 14, 14, 64)
strides=[1, 1, 1, 1], padding='SAME'))
l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],              # l2 shape=(?, 7, 7, 64)
strides=[1, 2, 2, 1], padding='SAME')
l2 = tf.nn.dropout(l2, p_keep_conv)

l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,                     # l3a shape=(?, 7, 7, 128)
strides=[1, 1, 1, 1], padding='SAME'))
l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],              # l3 shape=(?, 4, 4, 128)
strides=[1, 2, 2, 1], padding='SAME')
l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])    # reshape to (?, 2048)
l3 = tf.nn.dropout(l3, p_keep_conv)

l4 = tf.nn.relu(tf.matmul(l3, w4))
l4 = tf.nn.dropout(l4, p_keep_hidden)

pyx = tf.matmul(l4, w_o)
return pyx

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img
teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img

X = tf.placeholder("float", [None, 28, 28, 1])
Y = tf.placeholder("float", [None, 10])

w = init_weights([3, 3, 1, 32])       # 3x3x1 conv, 32 outputs
w2 = init_weights([3, 3, 32, 64])     # 3x3x32 conv, 64 outputs
w3 = init_weights([3, 3, 64, 128])    # 3x3x32 conv, 128 outputs
w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs
w_o = init_weights([625, 10])         # FC 625 inputs, 10 outputs (labels)

p_keep_conv = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

with tf.Session() as sess:
# you need to initialize all variables
tf.global_variables_initializer().run()

for i in range(100):
training_batch = zip(range(0, len(trX), batch_size),
range(batch_size, len(trX)+1, batch_size))
for start, end in training_batch:
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
p_keep_conv: 0.8, p_keep_hidden: 0.5})

test_indices = np.arange(len(teX)) # Get A Test Batch
np.random.shuffle(test_indices)
test_indices = test_indices[0:test_size]

print(i, np.mean(np.argmax(teY[test_indices], axis=1) ==
sess.run(predict_op, feed_dict={X: teX[test_indices],
p_keep_conv: 1.0,
p_keep_hidden: 1.0})))

0 0.95703125
1 0.9921875
2 0.9921875
3 0.98046875
4 0.97265625
5 0.98828125
6 0.99609375

7 0.99609375
8 0.99609375
9 0.98828125
10 0.98828125
11 0.9921875
12 0.98046875
13 0.99609375
14 0.9921875
15 0.99609375
16 1.0

【云栖快讯】云栖社区技术交流群汇总，阿里巴巴技术专家及云栖社区专家等你加入互动，老铁，了解一下？  详情请点击

### 网友评论

1F

1828726022281052 赞同
lusing