def gen_captcha_text_and_image(out_path='E:/data/captcha/images/'):
image = ImageCaptcha()
#获得随机生成的验证码
captcha_text = random_captcha_text()
#把验证码列表转为字符串
captcha_text = ''.join(captcha_text)
#生成验证码
captcha = image.generate(captcha_text)
mkdir(out_path)
image.write(captcha_text, out_path + captcha_text + '.jpg') # 写到文件
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
with tf.name_scope('train'):
# 使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
# 初始化变量
init = tf.global_variables_initializer()
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) # argmax返回一维张量中最大的值所在的位置
with tf.name_scope('accuracy'):
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
sess.run(init)
mkdir('E:/log/tensorboard')
writer = tf.summary.FileWriter('E:/log/tensorboard', sess.graph)
for epoch in range(10):
for batch in range(n_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})
acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))
# coding: utf-8
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from DeepLearning.utils import mkdir
log_file = r"E:\log\tensorflow_tensorboard"
mkdir(log_file)
MNIST_data = r"E:\data\MNIST_data_sets\MNIST_data"
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
with tf.name_scope("input"):
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784], name="input_x")
y = tf.placeholder(tf.float32, [None, 10], name="input_y")
with tf.name_scope("layer"):
with tf.name_scope("weights"):
with tf.name_scope("w"):
# 创建一个简单的神经网络
W = tf.Variable(tf.zeros([784, 10]), name="W")
with tf.name_scope("biases"):
b = tf.Variable(tf.zeros([10]))
with tf.name_scope("wx_plus_b"):
wx_plus_b = tf.matmul(x, W) + b
with tf.name_scope('optimization'):
# opt = tf.train.GradientDescentOptimizer(learning_rate=.2).minimize(loss)
opt = tf.train.AdamOptimizer(learning_rate=.4).minimize(loss)
# opt = tf.train.RMSPropOptimizer(learning_rate=.2).minimize(loss)****
correct_prediction = tf.equal(tf.argmax(out,1), tf.argmax(Y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
logdir = "E:/data/tensorboard/log"
with tf.Session() as sess:
sess.run(init)
mkdir(logdir)
writer = tf.summary.FileWriter(logdir,sess.graph)
avg_cost = 0
for Epoch in range(1000):
for i in range(n_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
opt_, c_ = sess.run([opt, loss], feed_dict={x: batch_xs, Y: batch_ys})
# avg_cost += c_ / n_batch
# if (i + 1) % display_step == 0:
# print("in-Epoch: {0} cost={1}".format(Epoch + 1, avg_cost))
# print("--------------------------->>>")
acc = sess.run(accuracy, feed_dict={x: mnist.test.images, Y: mnist.test.labels})
print("Epoch: {0} Acc={1}%".format(Epoch + 1, acc*100))
print("finished!")