TensorFlow-2 数字识别

步骤准备：

  1  数据准备：可以直接从 '/tmp/tensorflow/mnist/input_data' 中获取

  2 创建模型：x W b

  3 定义损失函数和优化形式（采用softmax分类器）

  4 启动会话（Session）

  5 训练模型

  6 测试并计算输出

  

其中softmax分类器的原理请参考：Softmax回归

程序：

#TensorFlow手写数目识别

import tensorflow.examples.tutorials.mnist as inputData
import tensorflow as tf
#导入命令行解析模块
import argparse
import sys


#Import data
data_dir='/tmp/tensorflow/mnist/input_data'
mnist=inputData.input_data.read_data_sets(data_dir,one_hot=True)

#Create model (x,W,b, Loss)
# The image size is of 28*28
#None means any length
x=tf.placeholder(tf.float32,[None, 784])
#W b
W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))
#Predict
y=tf.matmul(x,W)+b

#Define loss and optimizer
y_=tf.placeholder(tf.float32,[None,10])
  # The raw formulation of cross-entropy,
  #
  #   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
  #                                 reduction_indices=[1]))
                # tf.reduce_sum adds the elements in the second dimension of y,
                # due to the reduction_indices=[1] parameter.
                # tf.reduce_mean computes the mean over all the examples in the batch.
  #
  # can be numerically unstable.
  #
  # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
  # outputs of 'y', and then average across the batch.

loss=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y))
optimizer=tf.train.GradientDescentOptimizer(0.5).minimize(loss)

#Start Session
sess=tf.InteractiveSession()
#initial variables
tf.global_variables_initializer().run()

#Train --stochastic training
for _ in range(100):
    # 100 data points are randomly selected from the training data set
    batch_x,batch_y=mnist.train.next_batch(100)
    #trraining
    sess.run(optimizer,feed_dict={x:batch_x,y_:batch_y})

#Test
#tf.equal:  check if the pridction equals the label, if equal, True; else, False
#tf.argmax: obtain the opsition of the max value in row(1)
correct_prdiction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
#tf.cast: convert correct_prdiction to tf.float32
accuracy=tf.reduce_mean(tf.cast(correct_prdiction,tf.float32))
print(sess.run(accuracy,feed_dict={x:mnist.test.images,
                                   y_:mnist.test.labels}))

运行结果：0.8868