首页 > 编程知识 正文

tensorflow2.0,tensorflow算法

时间:2023-05-06 13:24:25 阅读:117511 作者:1823

1 .多曲线

1.1使用py plot方式导入编号as NP

import matplotlib.pyplot as plt

x=NP.arange (1,11,1 ) ) )。

PLT.plot(x,x * 2,label='First ' ) ) ) ) ) ) ) )。

PLT.plot(x,x * 3,label='Second ' ) ) ) ) ) ) ) ) )。

(PLT.plot(x,x * 4,label='Third ' () ) ) ) ) ) ) ) 65

PLT.legend(loc=0,ncol=1)参数: loc设定显示的位置,0为自适应; ncol设置要显示的列数

plt.show () )

1.2使用面向对象的import numpy as np

import matplotlib.pyplot as plt

x=NP.arange (1,11,1 ) ) )。

fig=plt.figure (

#ax.plot(x,x * 2) ) )。

#ax.legend(ryddydemo“)、loc=0) ) ) ) ) ) ) ) )。

plt.show () )

2 .双y轴曲线

合并双y轴曲线图例是一项很难的任务,对于MNIST,现在使用loss/accuracy绘制曲线。 导入tensor flow as TF

fromtensorflow.examples.tutorials.mnistimportinput _ data

导入时间

import matplotlib.pyplot as plt

import numpy as np

x _ data=TF.placeholder (TF.float 32,[None,784] ) ) ) ) )。

y _ data=TF.placeholder (TF.float 32,[None,10] ) ) ) )。

x_image=TF.reshape(x_data,[-1,28,28,1 ]

# convolve layer 1

filter1=TF.variable (TF.truncated _ normal ([ 5,5,1,6 ] ) )

bias1=TF.variable (TF.truncated _ normal ([6] ) )

conV1=TF.nn.conv2D(x_image,filter1,strides=[ 1,1,1 ],padding='SAME ' () ) ) ) ) ) ) )

h _ con v1=TF.nn.sigmoid (con v1 bias1) )。

max pool2=TF.nn.max _ pool (h _ con v1,k size=[ 1,2,2,1 ],strides=[ 1,2,2,1 ],padding='SAME ' )

# convolve layer 2

filter2=TF.variable (TF.truncated _ normal ([ 5,5,6,16 ] ) )

bias2=TF.variable (TF.truncated _ normal ([ 16 ] ) )

conV2=TF.nn.conv2D(maxpool2,filter2,strides=[ 1,1,1,1 ],padding='SAME ' ) () ) ) ) ) ) )。

h _ con v2=TF.nn.sigmoid (con v2 bias2) )。

max pool3=TF.nn.max _ pool (h _ con v2,k size=[ 1,2,2,1 ],strides=[ 1,2,2,1 ],padding='SAME ' )

# convolve layer 3

filter3=TF.variable (TF.truncated _ normal ([ 5,5,16,120 ] ) )

bias3=TF.variable (TF.truncated _ normal ([ 120 ] ) )

conV3=TF.nn.conv2D(maxpool3,filter3,strides=[ 1,1,1,1 ],padding='SAME ' ) ) ) ) )。

h _ con v3=TF.nn.sigmoid (con v3 bias3) )。

#全连接第1层

w _ fc1=TF.variable (TF.truncated _ normal ([7*7* 120,80 ] ) )

b _ fc1=TF.variable (TF.truncated _ normal ([8]

0]))

h_pool2_flat = tf.reshape(h_conv3, [-1, 7 * 7 * 120])

h_fc1 = tf.nn.sigmoid(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# full connection layer 2

W_fc2 = tf.Variable(tf.truncated_normal([80, 10]))

b_fc2 = tf.Variable(tf.truncated_normal([10]))

y_model = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

cross_entropy = - tf.reduce_sum(y_data * tf.log(y_model))

train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)

sess = tf.tsdxwz()

correct_prediction = tf.equal(tf.argmax(y_data, 1), tf.argmax(y_model, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess.run(tf.global_variables_initializer())

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

fig_loss = np.zeros([1000])

fig_accuracy = np.zeros([1000])

start_time = time.time()

for i in range(1000):

batch_xs, batch_ys = mnist.train.next_batch(200)

if i % 100 == 0:

train_accuracy = sess.run(accuracy, feed_dict={x_data: batch_xs, y_data: batch_ys})

print("step %d, train accuracy %g" % (i, train_accuracy))

end_time = time.time()

print("time:", (end_time - start_time))

start_time = end_time

print("********************************")

train_step.run(feed_dict={x_data: batch_xs, y_data: batch_ys})

fig_loss[i] = sess.run(cross_entropy, feed_dict={x_data: batch_xs, y_data: batch_ys})

fig_accuracy[i] = sess.run(accuracy, feed_dict={x_data: batch_xs, y_data: batch_ys})

print("test accuracy %g" % sess.run(accuracy, feed_dict={x_data: mnist.test.images, y_data: mnist.test.labels}))

# 绘制曲线

fig, ax1 = plt.subplots()

lns1 = ax1.plot(np.arange(1000), fig_loss, label="Loss")

# 按一定间隔显示实现方法

# ax2.plot(200 * np.arange(len(fig_accuracy)), fig_accuracy, 'r')

lns2 = ax2.plot(np.arange(1000), fig_accuracy, 'r', label="Accuracy")

# 合并图例

lns = lns1 + lns2

labels = ["Loss", "Accuracy"]

# labels = [l.get_label() for l in lns]

plt.legend(lns, labels, loc=7)

plt.show()

注:数据集保存在MNIST_data文件夹下

其实就是三步:

1)分别定义loss/accuracy一维数组fig_loss = np.zeros([1000])

fig_accuracy = np.zeros([1000])

# 按间隔定义方式:fig_accuracy = np.zeros(int(np.ceil(iteration / interval)))

2)填充真实数据fig_loss[i] = sess.run(cross_entropy, feed_dict={x_data: batch_xs, y_data: batch_ys})

fig_accuracy[i] = sess.run(accuracy, feed_dict={x_data: batch_xs, y_data: batch_ys})

3)绘制曲线fig, ax1 = plt.subplots()

lns1 = ax1.plot(np.arange(1000), fig_loss, label="Loss")

# 按一定间隔显示实现方法

# ax2.plot(200 * np.arange(len(fig_accuracy)), fig_accuracy, 'r')

lns2 = ax2.plot(np.arange(1000), fig_accuracy, 'r', label="Accuracy")

# 合并图例

lns = lns1 + lns2

labels = ["Loss", "Accuracy"]

# labels = [l.get_label() for l in lns]

plt.legend(lns, labels, loc=7)

以上这篇TensorFlow绘制loss/accuracy曲线的实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持爱安网。

版权声明:该文观点仅代表作者本人。处理文章:请发送邮件至 三1五14八八95#扣扣.com 举报,一经查实,本站将立刻删除。