参考博客链接:https://blog.csdn.net/qq_38269418/article/details/78991649
https://www.cnblogs.com/houjun/p/9016837.html
1.下载mnisit数据集,下载完成后不要解压 ,
input_data.read_data_sets函数读取的就是压缩文件
2.训练模型,代码如下
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('F:\MNIST_data', one_hot=True) #MNIST数据集所在路径
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
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')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
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)
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)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
saver = tf.train.Saver() #定义saver
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
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})
saver.save(sess, 'C:/Users/81286/Desktop/SAVE1/model.ckpt') #模型储存位置
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
3.制作测试图片,要求像素28*28的灰度图,图片格式为png
。目前还不会图像处理,采用将mnist数据集一维数组转变为二维图片的方法获得测试图片,代码如下
from tensorflow.examples.tutorials.mnist import input_data
import scipy.misc
import os
# 读取MNIST数据集。如果不存在会事先下载。
mnist = input_data.read_data_sets('F:\MNIST_data', one_hot=True)
# 我们把原始图片保存在MNIST_data/raw/文件夹下
# 如果没有这个文件夹会自动创建
save_dir = 'F:/MNIST_data/raw'
if os.path.exists(save_dir) is False:
os.makedirs(save_dir)
# 保存前20张图片
for i in range(20):
# 请注意,mnist.train.images[i, :]就表示第i张图片(序号从0开始)
image_array = mnist.train.images[i, :]
# TensorFlow中的MNIST图片是一个784维的向量,我们重新把它还原为28x28维的图像。
image_array = image_array.reshape(28, 28)
# 保存文件的格式为 mnist_train_0.jpg, mnist_train_1.jpg, ... ,mnist_train_19.jpg
filename = save_dir + 'mnist_train_%d.png' % i
# 将image_array保存为图片
# 先用scipy.misc.toimage转换为图像,再调用save直接保存。
scipy.misc.toimage(image_array, cmin=0.0, cmax=1.0).save(filename)
print('Please check: %s ' % save_dir)
4,将图片输入训练好的模型,测试识别准确度,代码如下:
y_ = tf.placeholder(tf.float32, [None, 10])
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')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
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)
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)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "C:/Users/81286/Desktop/SAVE1/model.ckpt") #使用模型,参数和之前的代码保持一致
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [result],keep_prob: 1.0}, session=sess)
print(h_conv2)
print('识别结果:')
print(predint[0])
5.识别结果:
6.有些图片识别度很低,模型整体识别度在80%左右,没有其他大佬们输的那么高。以后再找原因吧