【Tensorflow】2 softmax图像分类

1 概述

本程序所用数据集为MNIST，通过softmax激活函数训练样本，选择得到的标签数据one-hot verctor中的最大值作为结果。在学习率为0.01，batchsize为100，迭代次数为25次时，在测试集上的精确度到达了0.8316。

2 代码

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

# 解决版本不兼容问题
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)

# 导入读取MNIST数据包
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# 导入pylab绘图包
import pylab

# 重定义默认图
tf.reset_default_graph()

# 定义占位符
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 定义学习参数
W = tf.Variable(tf.random_normal([784, 10]))
b = tf.Variable(tf.zeros([10]))

# 定义预测值
# softmax用于多分类过程中，它将多个神经元的输出，映射到（0,1）区间内，可以看成概率来理解，从而来进行多分类
pred = tf.nn.softmax(tf.matmul(x, W) + b)

# 损失函数
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1))

# 定义学习率参数
learning_rate = 0.01

# 梯度下降优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# 定义迭代次数以及batch大小
training_epochs = 25
batch_size = 100
display_step = 1

# 启动session
with tf.Session() as sess:
    # 全局变量初始化
    sess.run(tf.global_variables_initializer())

    # 开始训练
    for epoch in range(training_epochs):
        avg_cost = 0

        # 求batch数量
        total_batch = int(mnist.train.num_examples / batch_size)

        # 对每一个batch进行训练
        for i in range(total_batch):
            # 获取batch中的样本值
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            # 一个batch里的梯度下降
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys})

            # 平均损失
            avg_cost += c / total_batch

        # 所有batch完成一次梯度下降
        # 展示迭代信息
        if (epoch + 1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))

    # 完成训练
    print("finished!")

    # 测试model
    correct_predoction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_predoction, tf.float32))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

    # 保存模型
    saver = tf.train.Saver()
    model_path = "log/521model.cpkt"
    save_path = saver.save(sess, model_path)
    print("Model saved in file: %s " % save_path)

    # 读取模型

    print("new session start！")

with tf.Session() as sess:
    # 全局变量初始化
    sess.run(tf.global_variables_initializer())

    # 模型加载
    saver.restore(sess, model_path)

    # 测试model
    correct_predoction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))

    # 计算准确率
    accuracy = tf.reduce_mean(tf.cast(correct_predoction, tf.float32))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

    output = tf.argmax(pred, 1)
    batch_xs, batch_ys = mnist.train.next_batch(2)
    outputval, predv = sess.run([output, pred], feed_dict={x: batch_xs})
    print(outputval, predv, batch_ys)

    im = batch_xs[0]
    im = im.reshape(-1, 28)
    pylab.imshow(im)
    pylab.show()

    im = batch_xs[1]
    im = im.reshape(-1, 28)
    pylab.imshow(im)
    pylab.show()

3 运行结果