- 包含: 1.层级的计算、2.训练的整体流程、3.tensorboard画图、4.保存/使用模型、5.总体代码(含详细注释)
1. 层级的计算
如上图,mnist手写数字识别的训练集提供的图片是 28 * 28 * 1的手写图像,初始识别的时候,并不知道一次要训练多少个数据,因此输入的规模为 [None, 784]. 由于最终的标签输出的是10个数据,因此输出的规模为[None, 10], 中间采取一个简单的全连接层作为隐藏层,规模为[784, 10]
2. 训练的整体流程
- 1.首先定义占位符:
# 训练集数据
x = tf.placehodler(tf.float32, [None, 784])
# 训练集标签
y_true = tf.placeholder(rf.int32, [None, 10])
- 2.建立模型
# 随机生成权重矩阵和偏置
# 权重
weight = tf.Variable(tf.random_normal([784, 10], mean =0.0, stddev=1.0), name="weight")
# 偏置
bias = tf.Variable(tf.constant(0.0, shape=[10]))
# 预测
y_predict = tf.matmul(x, weight) + bias
- 3.计算平均损失
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_predict))
- 4.优化方案(梯度下降)
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
- 5.计算损失率
equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict, 1))
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
3. tensorboard使用
# 按作用域命名
with tf.variable_scope("data"):
pass
with tf.variable_scope("full_layer"):
pass
# 收集变量(单维度)
tf.summary.scalar("losses", loss)
tf.summary.scalar("acc", accuracy)
# 收集变量(多维度)
tf.summary.histogram("weightes", weight)
tf.summary.histogram("biases", bias)
# 将训练的每一步写入
with tf.Session() as sess:
# 建立events文件,然后写入
filewriter = tf.summary.FileWriter("./tmp/", graph=sess.graph)
for i in range(5000):
# 写入每步训练的值
summary = sess.run(merged, feed_dict={x: mnist_x, y_true: mnist_y})
filewriter.add_summary(summary, i)
- 4.模型的保存/使用
# 模型的初始化(一般写在Session上面)
saver = tf.train.Saver()
# Session中为模型保存分配资源
with tf.Session() as sess:
# 保存模型
saver.save(sess, "./tmp/ckpt/fc_model")
# 加载模型
saver.restore(sess, "./tmp/ckpt/fc_model")
# 预测
for i in range(100):
x, y = mnist.test.next_batch(1)
predict = tf.argmax(sess.run(y_predict, feed_dict={x: x_test, y_true: y_test}), 1).eval()
5.总体代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_integer("is_train", 1, "0: 预测, 1: 训练")
"""
单层(全连接层)实现手写数字识别
特征值[None, 784] 目标值[None, 10]
1、 定义数据占位符
特征值[None, 784] 目标值[None, 10]
2、 建立模型
随机初始化权重和偏置
w[784, 10] b
y_predict = tf.matmul(x, w) + b
3、 计算损失
loss: 平均样本的损失
4、 梯度下降优化
5、 准确率计算:
equal_list = tf.equal(tf.argmax(y, 1), tf.argmax(y_label, 1))
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
"""
def ful_connected():
# 读取数据
mnist = input_data.read_data_sets("./data/mnist/input_data/", one_hot=True)
# 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、 建立一个全连接层的神经网络 w [784, 10] b [10]
with tf.variable_scope("full_layer"):
# 随机初始化权重和偏置
weight = tf.Variable(tf.random_normal([784, 10], mean=0.0, stddev=1.0), name="weight")
bias = tf.Variable(tf.constant(0.0, shape=[10]))
# 预测None个样本的输出结果 [None, 784] * [784, 10] + [10] = [None, 10]
y_predict = tf.matmul(x, weight) + bias
# 3、 求出所有样本的损失,然后求平均值
with tf.variable_scope("softmax"):
# 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(0.1).minimize(loss)
# 5、 计算准确率
with tf.variable_scope("count_acc"):
equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict, 1))
# equal_list None个样本 [1, 0, 1, 0, 1, 1, ....]
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
# 收集变量(单维度)
tf.summary.scalar("losses", loss)
tf.summary.scalar("acc", accuracy)
# 收集变量(高维度)
tf.summary.histogram("weightes", weight)
tf.summary.histogram("biases", bias)
# 定义一个初始化变量的op
init_op = tf.global_variables_initializer()
# 定义合并变量
merged = tf.summary.merge_all()
# 保存模型
saver = tf.train.Saver()
# 开启会话训练
with tf.Session() as sess:
# 初始化变量
sess.run(init_op)
# 建立events文件,然后写入
filewriter = tf.summary.FileWriter("./tmp/", graph=sess.graph)
if FLAGS.is_train == 0:
# 迭代步骤去训练,更新参数预测
for i in range(5000):
# 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})
filewriter.add_summary(summary, i)
# 打印损失
print("训练第%d步,准确率为:%f" % (i, sess.run(accuracy, feed_dict={x: mnist_x, y_true: mnist_y})))
# 保存模型
saver.save(sess, "./tmp/ckpt/fc_model")
else:
# 加载模型
saver.restore(sess, "./tmp/ckpt/fc_model")
# 预测
for i in range(100):
# 每次测试一张图片
x_test, y_test = mnist.test.next_batch(1)
print("第%d张图片是: %d,预测结果是:%d" % (
i,
tf.argmax(y_test, 1).eval(),
tf.argmax(sess.run(y_predict, feed_dict={x: x_test, y_true: y_test}), 1).eval()
))
return None
if __name__ == "__main__":
ful_connected()
6. cnn版本的mnist
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
"""
使用卷积神经网络实现 mnist的手写数据集识别
"""
"""
input: [None, 784]
output: [784, 10]
进入卷积时,首先需要改变图片的形状 [None, 784] --> [None, 28, 28, 1]
卷积网络设计:
· 第一层卷积层: 32 * core(5*5)、strides(1)、padding="SAME"
· 此时大小为: [None, 28, 28, 32]
· 激活
· 池化: 2*2、 strides(2)、 padding="SAME"
· 此时大小为: [None, 14, 14, 32]
· 第二层卷积层: 64 * core(5*5)、 strides(1)、 padding="SAME"
· 此时大小为: [None, 14, 14, 64]
· 激活
· 池化: 2*2、 strides(2)、 padding="SAME"
· 此时大小为: [None, 7, 7, 64]
· 全连接层: [None, 7*7*64] * [7*7*64, 10] + bias = [None, 10]
"""
# 定义个初始化权重的函数
def weight_variable(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():
"""
自定义的卷积模型
:return:
"""
# 1、准备数据的占位符 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: 5*5*1, 32个, strides = 1 、激活、池化
with tf.variable_scope("conv1"):
# 随机初始化权重,偏置[32]
w_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variables([32])
# 对x进行形状的改变 [None, 784] -> [None, 28, 28, 1]
x_reshape = tf.reshape(x, [-1, 28, 28, 1])
# [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 2*2, strides2 [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 5*5*32, 64个filter, strides= 1
with tf.variable_scope("conv2"):
w_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variables([64])
# 卷积、激活、池化计算
# [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 2*2, strides2 [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]
# 随机初始化权重和偏置
w_fc = weight_variable([7 * 7 * 64, 10])
b_fc = bias_variables([10])
# 修改形状: [None, 7, 7, 64] -> [None, 7*7*64]
x_fc_reshape = tf.reshape(x_pool2, [-1, 7 * 7 * 64])
# 矩阵运算,得出每个样本的10个结果
y_predict = tf.matmul(x_fc_reshape, w_fc) + b_fc
return x, y_true, y_predict
def conf_fc():
# 1、 读取数据
mnist = input_data.read_data_sets("./data/mnist/input_data/", one_hot=True)
# 2、 定义模型,得出输出
x, y_true, y_predict = model()
# 3、 求出所有的损失,然后求平均值
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(0.00005).minimize(loss)
# 5、 计算准确率
with tf.variable_scope("acc"):
equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict, 1))
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
# 定义一个初始变量op
init_op = tf.global_variables_initializer()
# 开启会话运行
with tf.Session() as sess:
sess.run(init_op)
# 循环去训练
for i in range(1000):
# 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})
# 打印损失
print("训练第%d步,准确率为:%f" % (i, sess.run(accuracy, feed_dict={x: mnist_x, y_true: mnist_y})))
return None
if __name__ == "__main__":
conf_fc()
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
