使用Tensorflow制作球鞋识别模型（三）——建立神经网络

最新推荐文章于 2022-08-23 15:45:33 发布

WellTung_666

最新推荐文章于 2022-08-23 15:45:33 发布

阅读量762

点赞数

分类专栏： Tensorflow 文章标签：深度学习 tensorflow 神经网络

本文链接：https://blog.csdn.net/welltung_666/article/details/89244148

版权

Tensorflow 专栏收录该内容

10 篇文章 3 订阅

订阅专栏

在上一篇博客使用Tensorflow制作球鞋识别模型（二）——图片输入处理中已经介绍了图片输入处理，至此图片准备和处理处理已经结束，接下来就是建立神经网络。

网络结构

神经网络包含3层卷积+池化层，2层全连接层，使用ReLu激活函数，Softmax函数做分类器。

定义神经网络

导入包

首先导入所需的包

import tensorflow as tf

定义函数

def weight_variable(shape, n):
    # tf.truncated_normal(shape, mean, stddev)从截断的正态分布中输出随机值
    # stddev是标准差，默认最大为1，最小为-1，均值为0
    initial = tf.truncated_normal(shape, stddev=n, dtype=tf.float32)
    return initial

def bias_variable(shape):
    # 创建一个结构为shape矩阵，初始化所有值为0.1
    initial = tf.constant(0.1, shape=shape, dtype=tf.float32 )
    return initial

def conv2d(x, W):
    # 卷积函数，步长为1，边缘自动补0
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x, name):
    # 尺寸为3×3，步长为2的×2的最大池化层
    return tf.nn.max_pool(x, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

卷积神经网络

def inference(images, batch_size, n_classes):

    # 卷积层1
    with tf.variable_scope('conv1') as scope:
        w_conv1 = tf.Variable(weight_variable([3, 3, 3, 64], 1.0), name='weights', dtype=tf.float32)
        b_conv1 = tf.Variable(bias_variable([64]), name='biases', dtype=tf.float32)
        h_conv1 = tf.nn.relu(conv2d(images, w_conv1) + b_conv1, name='conv1')

    # 池化层1
    with tf.variable_scope('pooling1_lrn') as scope:
        pool1 = max_pool_2x2(h_conv1, 'pooling1')
        # 卷积池化后使用LRN（局部相应归一化）增强模型的泛化能力
        norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001/9.0, beta=0.75, name='norm1')

    # 卷积层2
    with tf.variable_scope('conv2') as scope:
        w_conv2 = tf.Variable(weight_variable([3, 3, 64, 32], 0.1), name='weights', dtype=tf.float32)
        b_conv2 = tf.Variable(bias_variable([32]), name='biases', dtype=tf.float32)
        h_conv2 = tf.nn.relu(conv2d(norm1, w_conv2) + b_conv2, name='conv2')
        
    # 池化层2
    with tf.variable_scope('pooling2_lrn') as scope:
        pool2 = max_pool_2x2(h_conv2, 'pooling2')
        norm2 = tf.nn.lrn(pool2, depth_radius=0.75, bias=1.0, alpha=1.0/0.9, beta=0.75, name='norm2')

    # 卷积层3
    with tf.variable_scope('conv3') as scope:
        w_conv3 = tf.Variable(weight_variable([3, 3, 32, 16], 0.1), name='weights', dtype=tf.float32)
        b_conv3 = tf.Variable(bias_variable([16]), name='biases', dtype=tf.float32)
        h_conv3 = tf.nn.relu(conv2d(norm2, w_conv3) + b_conv3, name='conv3')
        # 池化层3
    with tf.variable_scope('pooling3_lrn') as scope:
        pool3 = max_pool_2x2(h_conv3, 'pooling2')
        norm3 = tf.nn.lrn(pool3, depth_radius=4, bias=1.0, alpha=1.0 / 0.9, beta=0.75, name='norm3')

    # 全连接层1
    with tf.variable_scope('local3') as scope:
        reshape = tf.reshape(norm3, shape=[batch_size, -1])
        dim = reshape.get_shape()[1].value
        w_fc1 = tf.Variable(weight_variable([dim, 128], 0.005),  name='weights', dtype=tf.float32)
        b_fc1 = tf.Variable(bias_variable([128]), name='biases', dtype=tf.float32)
        h_fc1 = tf.nn.relu(tf.matmul(reshape, w_fc1) + b_fc1, name=scope.name)

    # 全连接层2
    with tf.variable_scope('local4') as scope:
        w_fc2 = tf.Variable(weight_variable([128, 128], 0.005), name='weights', dtype=tf.float32)
        b_fc2 = tf.Variable(bias_variable([128]), name='biases', dtype=tf.float32)
        h_fc2 = tf.nn.relu(tf.matmul(h_fc1, w_fc2) + b_fc2, name=scope.name)

    h_fc2_dropout = tf.nn.dropout(h_fc2, 0.5)

    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.Variable(weight_variable([128, n_classes], 0.005), name='weights', dtype=tf.float32)
        biases = tf.Variable(bias_variable([n_classes]), name='biases', dtype=tf.float32)
        softmax_linear = tf.add(tf.matmul(h_fc2_dropout, weights), biases, name='softmax_linear')
    return softmax_linear

loss计算和优化

def losses(logits, labels):
    with tf.variable_scope('loss') as scope:
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='xentropy_per_example')
        loss = tf.reduce_mean(cross_entropy, name='loss')
        tf.summary.scalar(scope.name + '/loss', loss)
    return loss


def trainning(loss, learning_rate):
    with tf.name_scope('optimizer'):
        optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
        global_step = tf.Variable(0, name='global_step', trainable=False)
        train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op

准确率计算

def evaluation(logits, labels):
    with tf.variable_scope('accuracy') as scope:
    # tf.nn.in_top_k（prediction, target, K）计算预测的结果和实际结果的是否相等
        correct = tf.nn.in_top_k(logits, labels, 1)
        accuracy = tf.reduce_mean(tf.cast(correct, tf.float16))
        tf.summary.scalar(scope.name + '/accuracy', accuracy)
    return accuracy

全部代码

import tensorflow as tf

def weight_variable(shape, n):
    initial = tf.truncated_normal(shape, stddev=n, dtype=tf.float32)
    return initial

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape, dtype=tf.float32 )
    return initial

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x, name):
    return tf.nn.max_pool(x, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

def inference(images, batch_size, n_classes):

    # 卷积层1
    with tf.variable_scope('conv1') as scope:
        w_conv1 = tf.Variable(weight_variable([3, 3, 3, 64], 1.0), name='weights', dtype=tf.float32)
        b_conv1 = tf.Variable(bias_variable([64]), name='biases', dtype=tf.float32)
        h_conv1 = tf.nn.relu(conv2d(images, w_conv1) + b_conv1, name='conv1')

    # 池化层1
    with tf.variable_scope('pooling1_lrn') as scope:
        pool1 = max_pool_2x2(h_conv1, 'pooling1')
        norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001/9.0, beta=0.75, name='norm1')

    # 卷积层2
    with tf.variable_scope('conv2') as scope:
        w_conv2 = tf.Variable(weight_variable([3, 3, 64, 32], 0.1), name='weights', dtype=tf.float32)
        b_conv2 = tf.Variable(bias_variable([32]), name='biases', dtype=tf.float32)
        h_conv2 = tf.nn.relu(conv2d(norm1, w_conv2) + b_conv2, name='conv2')
    # 池化层2
    with tf.variable_scope('pooling2_lrn') as scope:
        pool2 = max_pool_2x2(h_conv2, 'pooling2')
        norm2 = tf.nn.lrn(pool2, depth_radius=0.75, bias=1.0, alpha=1.0/0.9, beta=0.75, name='norm2')

    # 卷积层3
    with tf.variable_scope('conv3') as scope:
        w_conv3 = tf.Variable(weight_variable([3, 3, 32, 16], 0.1), name='weights', dtype=tf.float32)
        b_conv3 = tf.Variable(bias_variable([16]), name='biases', dtype=tf.float32)
        h_conv3 = tf.nn.relu(conv2d(norm2, w_conv3) + b_conv3, name='conv3')
        # 池化层3
    with tf.variable_scope('pooling3_lrn') as scope:
        pool3 = max_pool_2x2(h_conv3, 'pooling2')
        norm3 = tf.nn.lrn(pool3, depth_radius=4, bias=1.0, alpha=1.0 / 0.9, beta=0.75, name='norm3')

    # 全连接层
    with tf.variable_scope('local3') as scope:
        reshape = tf.reshape(norm3, shape=[batch_size, -1])
        dim = reshape.get_shape()[1].value
        w_fc1 = tf.Variable(weight_variable([dim, 128], 0.005),  name='weights', dtype=tf.float32)
        b_fc1 = tf.Variable(bias_variable([128]), name='biases', dtype=tf.float32)
        h_fc1 = tf.nn.relu(tf.matmul(reshape, w_fc1) + b_fc1, name=scope.name)

    # 全连接层2
    with tf.variable_scope('local4') as scope:
        w_fc2 = tf.Variable(weight_variable([128, 128], 0.005), name='weights', dtype=tf.float32)
        b_fc2 = tf.Variable(bias_variable([128]), name='biases', dtype=tf.float32)
        h_fc2 = tf.nn.relu(tf.matmul(h_fc1, w_fc2) + b_fc2, name=scope.name)

    h_fc2_dropout = tf.nn.dropout(h_fc2, 0.5)

    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.Variable(weight_variable([128, n_classes], 0.005), name='weights', dtype=tf.float32)
        biases = tf.Variable(bias_variable([n_classes]), name='biases', dtype=tf.float32)
        softmax_linear = tf.add(tf.matmul(h_fc2_dropout, weights), biases, name='softmax_linear')
    return softmax_linear

def losses(logits, labels):
    with tf.variable_scope('loss') as scope:
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='xentropy_per_example')
        loss = tf.reduce_mean(cross_entropy, name='loss')
        tf.summary.scalar(scope.name + '/loss', loss)
    return loss

def trainning(loss, learning_rate):
    with tf.name_scope('optimizer'):
        optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
        global_step = tf.Variable(0, name='global_step', trainable=False)
        train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op

def evaluation(logits, labels):
    with tf.variable_scope('accuracy') as scope:
        correct = tf.nn.in_top_k(logits, labels, 1)
        accuracy = tf.reduce_mean(tf.cast(correct, tf.float16))
        tf.summary.scalar(scope.name + '/accuracy', accuracy)
    return accuracy