tensorflow-卷积神经网络mnist数字识别问题

前言：卷积神经网络mnis数字识别问题

第一步：源码

import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.saved_model.model_utils.mode_keys import is_train
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2'
tf.app.flags.DEFINE_integer("is_train", 1, "指定模型是训练还是预测")
FLAGS = tf.app.flags.FLAGS


# 定义一个初始化权重的函数,传入参数的形状
def weight_variables(shape):
    w = tf.Variable(tf.random_normal(shape=shape, mean=0.0, stddev=1.0))
    return w


# 定义一个初始化偏置的函数
def bias_variables(shape):
    b = tf.Variable(tf.constant(0.0, shape=shape))
    return b


def model():
    """
    自定义卷积模型
    :return:
    """
    # 1.建立数据的占位符 x [None, 784]  y_true [None, 10]
    with tf.variable_scope("data"):
        x = tf.placeholder(tf.float32, [None, 784])
        y_true = tf.placeholder(tf.int32, [None, 10])
    # 2.一卷积层,卷积，激活，池化
    with tf.variable_scope("cov1"):
        # 随机初始化权重,初始化偏置
        w_conv1 = weight_variables([5, 5, 1, 32])
        b_conv1 = bias_variables([32])

        # 对x进行形状的改变[None, 784]   [None, 28, 28, 1],因为改变的行数不知道
        # 故行数那里填-1,这里改变形状采用的是动态改变形状
        x_reshape = tf.reshape(x, [-1, 28, 28, 1])

        # 步长为1，这样写表示上下左右移动的步长都是1,再进行激活
        # [None, 28, 28, 1]---------->[None, 28, 28, 32]
        x_relu1 = tf.nn.relu(tf.nn.conv2d(x_reshape, w_conv1, strides=[1, 1, 1, 1], padding="SAME") + b_conv1)

        # 池化窗口大小 2* 2，步长为2，[None, 28, 28, 32]-------->[None, 14, 14, 32]
        x_pool1 = tf.nn.max_pool(x_relu1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")

    # 3.二卷积层,卷积，激活，池化
    with tf.variable_scope("cov2"):
        # 随机初始化权重,初始化偏置
        w_conv2 = weight_variables([5, 5, 32, 64])
        b_conv2 = bias_variables([64])

        # 64个过滤器，步长为1，padding = "SAME" , bias=64
        # [None, 14, 14, 32]---------->[None, 14, 14, 64]
        x_relu2 = tf.nn.relu(tf.nn.conv2d(x_pool1, w_conv2, strides=[1, 1, 1, 1], padding="SAME") + b_conv2)

        # 池化窗口大小 2* 2，步长为2，[None, 14, 14, 64]-------->[None, 7, 7, 64]
        x_pool2 = tf.nn.max_pool(x_relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")

    # 4.全连接层,[None, 7, 7, 64]----->[None, 7*7*64] * [7*7*64, 10] +[10] = [None, 10]
    with tf.variable_scope("full_connected"):
        # 1.随机初始化权重和偏置
        w_fc = weight_variables([7*7*64, 10])
        b_fc = bias_variables([10])

        # 2.进行矩阵运算，得出每个样本的10个结果,修改形状
        x_reshape1 = tf.reshape(x_pool2, [-1, 7*7*64])
        y_predict = tf.matmul(x_reshape1, w_fc) + b_fc

    return x, y_true, y_predict


def conv_fc():

    # 1.获取真实数据
    mnist = input_data.read_data_sets("./data", one_hot=True)

    # 2.定义模型，得出输出
    x, y_true, y_predict = model()

    # 3.进行交叉熵损失计算
    with tf.variable_scope("soft_cross"):
        # 求平均交叉熵损失
        loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_predict))

    # 4.梯度下降求出损失
    with tf.variable_scope("optimizer"):
        train_op = tf.train.GradientDescentOptimizer(0.001).minimize(loss)

    # 5.计算准确率
    with tf.variable_scope("accuracy"):
        equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict, 1))
        # equal_list None个样本   [1, 1, 1, 0, ..............1]]
        accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))

    # 定义一个初始化变量的op
    init_op = tf.global_variables_initializer()

    # 收集变量,单个数字值收集
    tf.summary.scalar("losses", loss)
    tf.summary.scalar("acc", accuracy)

    # 定义一个合并变量的op
    merged = tf.summary.merge_all()

    # 定义一个保存模型的实例op
    saver = tf.train.Saver()

    # 开启会话运行
    with tf.Session() as sess:
        sess.run(init_op)
        # 建立events文件，然后写入
        fw = tf.summary.FileWriter("./tmp/summary/test", graph=sess.graph)

        # 迭代步数去训练，更新参数预测
        for i in range(100):
            # 每一次给50个数据进行训练，取出真实存在的特征值和目标值
            mnist_x, mnist_y = mnist.train.next_batch(50)
            # 运行train_op训练
            sess.run(train_op, feed_dict={x: mnist_x, y_true: mnist_y})

            # 写入每步训练的值
            summary = sess.run(merged, feed_dict={x: mnist_x, y_true: mnist_y})
            # 添加到写入的文件当中
            fw.add_summary(summary, i)

            print("训练第%d步，准确率为:%f" % (i, sess.run(accuracy, feed_dict={x: mnist_x, y_true: mnist_y})))
        saver.save(sess, "./tmp/summary/smodl/fc_model")
    return None


if __name__ == "__main__":
    conv_fc()

第二部：代码运行结果和可视化参数变化情况