tensorflow自己写的训练集用标准mnist数据集看测试效果（6）

训练集是自己写的，一共5500张，测试集选用官方下载的测试集，用了300张，这里测试集需要略作修改，按照https://blog.csdn.net/it_job/article/details/80540877操作，这里测试集可以换成自己写的

按照https://blog.csdn.net/it_job/article/details/80547206操作，将数据拷贝到MNIST_data中,再使用gzip命令压缩

现在需要修改验证集的数量，文件路径/home/xy/anaconda3/install/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets
修改mnist.py中的函数
def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=dtypes.float32,
                   reshape=True,
                   validation_size=500,#原始为5000,为验证数据集，做修改，大约训练集中10%做验证，这里改为500
                   seed=None):

cd到当前目录

执行python '/home/xy/highschool_myOwn615/train.py'

train.py代码为

import tensorflow as tf
#导入数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#去除加速sse的warning
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
#x为训练图像,y_为训练图像标签
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
#权重偏置初始化
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

#权重在初始化时应该加入少量的噪声来打破对称性以及避免0梯度，避免神经元节点输出恒为0的问题（dead neurons）
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


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


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


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

#第一层卷积层，32个卷积核去分别关注32个特征
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])#将单张图片从784维向量重新还原为28x28的矩阵图片，-1表示取出所有的数据
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#第二层卷积层
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#全连接层
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#使用Dropout，训练时为0.5，测试时为1，keep_prob表示保留不关闭的神经元的比例
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#把1024维的向量转换成10维，对应10个类别
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
#交叉熵
cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
#定义train_step
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#定义测试准确率
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  
#创建Session和变量初始化
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
#标准训练是20000步,这里为节约时间训练1000步
for i in range(1000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:#每100步输出一次在验证集上的准确度
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))

  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

#输出在测试集上的准确度
print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

训练结果

训练精度不高，可能是图片数量不够，没进行调参等原因，不过流程已经走通了。

到这里就结束了

tensorflow自己写的训练集用标准mnist数据集看测试效果（6）

猜你喜欢