Tensorflow卷积神经网络实现MNIST手写数据集识别

模型建的不好，最终只有85%左右的准确率，后面继续改进吧

#卷积神经网络API
   卷积层：tf.nn.conv2d(input,   #输入张量，具有[batch, height, width, channel]
               filter,   #过滤器大小[filter_height, filter_width, in_channels,out_channels]
               strides,#步长，一般为1
               padding   #SAME VALID,same为填充0，输出结论与输入结论的长宽一样
               )

   池化层：tf.nn.max_pool(value,   #[batch, height, width,channels]
               ksize,   #池化窗口大小
               strides，   #步长大小
               padding   #填充类型，SAME or VALID
               )

#卷积神经网络识别mnist
import tensorflow as tf
import os
from tensorflow.examples.tutorials.mnist import input_data

def init_weight(shape):
   """
   初始化权重参数
   """
   w = tf.Variable(tf.random_normal(shape = shape, mean=0.0, stddev=1.0))
   return w

def init_bias(shape):
   """
   初始化偏置参数
   """
   b = tf.Variable(tf.random_normal(shape = shape, mean=0.0, stddev=1.0))
   return b

def modol():
   """
   卷积神经网络模型
   """
   # 1、准备数据占位符 x[None, 784], y[None, 10]
   with tf.variable_scope("Input_data"):
       x = tf.placeholder(tf.float32, [None, 784])
       y_true = tf.placeholder(tf.int32, [None, 10])

# 2、卷积层1
with tf.variable_scope("Conv1"):

       # 随机初始化参数
       w1 = init_weight([5,5,1,32])
       b1 = init_bias([32])

       # 改变x从[None,784] -> [None,28, 28, 1]
       x_reshape = tf.reshape(x, [-1, 28, 28, 1])

       # 进行卷积操作,x_relu[None,28,28,32]
       x1_relu = tf.nn.relu(tf.nn.conv2d(x_reshape, w1, strides = [1,1,1,1], padding="SAME") + b1)

#池化层
x1_pool = tf.nn.max_pool(x1_relu, ksize=[1,2,2,1], strides = [1,2,2,1], padding="SAME")

   # 3、卷积层2:输入为：[None,14,14,32]
       # 随机初始化参数
       w2 = init_weight([5,5,32,64])
       b2 = init_bias([64])

# 进行卷积操作,x_relu[None,14,14,64]
x2_relu = tf.nn.relu(tf.nn.conv2d(x1_pool, w2, strides = [1,1,1,1], padding="SAME") + b2)

#池化层[None,14,14,64] -> [None,7,7,64]
x2_pool = tf.nn.max_pool(x2_relu, ksize=[1,2,2,1], strides = [1,2,2,1], padding="SAME")

# 4、全连接层，输入为[None,7,7,64] * [7*7*64,10] = [None,10]

       #随机初始化权重和偏置
       w_fc = init_weight([7*7*64,10])
       b_fc = init_bias([10])

#修改矩阵大小[None,7,7,64] -> [None,7*7*64]
fc_reshape = tf.reshape(x2_pool, [-1,7*7*64])

       #进行矩阵运算[None, 10]
       y_predict = tf.matmul(fc_reshape, w_fc) + b_fc
   return x, y_true, y_predict

def conv_fc():

   mnist = input_data.read_data_sets("./mnist/input_data/", one_hot=True)
   x, y_true, y_predict = modol()

   #计算交叉熵损失
   with tf.variable_scope("soft_cross"):
       loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_true, logits = y_predict))

   with tf.variable_scope("opitmizer"):
       train_op = tf.train.GradientDescentOptimizer(0.0001).minimize(loss)

   with tf.variable_scope("accuracy"):
       equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict,1))
       accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))

init_op = tf.global_variables_initializer()
print("asd")

with tf.Session() as sess:

sess.run(init_op)

       #循环训练
       for i in range(5000):
           # API获取一个训练batch
           mnixt_x, mnist_y = mnist.train.next_batch(50)

           # 运行op训练
           sess.run(train_op, feed_dict = {x: mnixt_x, y_true: mnist_y})
           print("after %d times of trainings, accuracy is %f" %
                   (i, sess.run(accuracy, feed_dict = {x: mnixt_x, y_true: mnist_y})))

return None

if __name__ == '__main__':
conv_fc()

Tensorflow卷积神经网络实现MNIST手写数据集识别

猜你喜欢