# Classification 分类学习

## MNIST 数据

先准备数据（MNIST库）

```python
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
```

**MNIST**库是手写体数字库

![](https://morvanzhou.github.io/static/results/tensorflow/5_01_1.png)

数据中包含55000张训练图片，每张图片的分辨率是28×28，所以训练网络输入是28×28=784个像素数

## 搭建网络

```python
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28

#输出是数字0到9，共10类
ys = tf.placeholder(tf.float32, [None, 10])
prediction = add_layer(xs, 784, 10, activation_function=tf.nn.softmax)
```

输入数据是784个特征，输出数据是10个特征，激励采用**softmax**函数

网络结构图:

![](https://morvanzhou.github.io/static/results/tensorflow/5_01_2.png)

## Cross entropy loss

loss函数（即最优化目标函数）选用交叉熵函数。交叉熵用来衡量预测值和真实值的相似程度，如果完全相同，它们的交叉熵等于零。

```python
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
__reduction_indices=[1])) # loss
__
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()

sess.run(tf.global_variables_initializer())
```

## 训练

每次只取100张图片

```python
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys})
if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))
```

![](https://morvanzhou.github.io/static/results/tensorflow/5_01_3.png)

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

tf.set_random_seed(1)
np.random.seed(1)

# fake data
n_data = np.ones((100, 2))
x0 = np.random.normal(2*n_data, 1)      # class0 x shape=(100, 2)
y0 = np.zeros(100)                      # class0 y shape=(100, 1)
x1 = np.random.normal(-2*n_data, 1)     # class1 x shape=(100, 2)
y1 = np.ones(100)                       # class1 y shape=(100, 1)
x = np.vstack((x0, x1))  # shape (200, 2) + some noise
y = np.hstack((y0, y1))  # shape (200, )

# plot data
plt.scatter(x[:, 0], x[:, 1], c=y, s=100, lw=0, cmap='RdYlGn')
plt.show()

tf_x = tf.placeholder(tf.float32, x.shape)     # input x
tf_y = tf.placeholder(tf.int32, y.shape)     # input y

# neural network layers
l1 = tf.layers.dense(tf_x, 10, tf.nn.relu)          # hidden layer
output = tf.layers.dense(l1, 2)                     # output layer

loss = tf.losses.sparse_softmax_cross_entropy(labels=tf_y, logits=output)           # compute cost
accuracy = tf.metrics.accuracy(          # return (acc, update_op), and create 2 local variables
    labels=tf.squeeze(tf_y), predictions=tf.argmax(output, axis=1),)[1]
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.05)
train_op = optimizer.minimize(loss)

sess = tf.Session()                                                                 # control training and others
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init_op)     # initialize var in graph

plt.ion()   # something about plotting
for step in range(100):
    # train and net output
    _, acc, pred = sess.run([train_op, accuracy, output], {tf_x: x, tf_y: y})
    if step % 2 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x[:, 0], x[:, 1], c=pred.argmax(1), s=100, lw=0, cmap='RdYlGn')
        plt.text(1.5, -4, 'Accuracy=%.2f' % acc, fontdict={'size': 20, 'color': 'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()
```

![](https://camo.githubusercontent.com/03cf1c4921b6e80da7710c117164b27675351118/68747470733a2f2f6d6f7276616e7a686f752e6769746875622e696f2f7374617469632f726573756c74732f746f7263682f312d312d332e676966)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://baozoulin.gitbook.io/tensorflow/gao-jie-nei-rong/classification-fen-lei-xue-xi.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.