基于一个隐藏层神经网络的手写数字识别

基于一个隐藏层神经网络的手写数字识别

import tensorflow as tf
import os
import matplotlib.pyplot as plt
import numpy as np

#下载读取数据
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("./MNIST_data/",one_hot=True)

#模型构建

#输入数据占位符
x=tf.placeholder(tf.float32,[None,784],name="X")#每张图片有28*28个像素点
y=tf.placeholder(tf.float32,[None,10],name="Y")#10个类别

#构建隐藏层
H1_NN=256
w1=tf.Variable(tf.random_normal([784,H1_NN]),name="W1")
b1=tf.Variable(tf.zeros([H1_NN]),name="B1")
y1=tf.nn.relu(tf.matmul(x,w1)+b1)

#构建输出层
w2=tf.Variable(tf.random_normal([H1_NN,10]),name="W2")
b2=tf.Variable(tf.zeros([10]),name="B2")

forword=tf.matmul(y1,w2)+b2 #定义前向计算
pred=tf.nn.softmax(forword) #结果分类

#设置训练参数
train_epochs=40 #训练轮次
batch_size=50 #单次训练样本数（批次大小）
total_batch=int(mnist.train.num_examples/batch_size) #一轮训练批次
display_step=1 #显示粒度
learning_rate=0.01 #学习率

#损失函数
#log(pred)不稳定
# loss_function=tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1)) #交叉熵损失
loss_function=tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=forword,labels=y))

#优化器
optimizer=tf.train.AdamOptimizer(learning_rate).minimize(loss_function)

#定义计算准确率
corr_prediction=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(corr_prediction,tf.float32))#转换成浮点数计算平均值

# 声明会话和初始化
#记录训练开始时间
from time import time
startTime=time()

sess=tf.Session()
init=tf.global_variables_initializer()
sess.run(init)

#模型训练
for epoch in range(train_epochs):
    for batch in range(total_batch):
        xs, ys = mnist.train.next_batch(batch_size)  # 读取批次数据
        sess.run(optimizer, feed_dict={x: xs, y: ys})  # 执行批次训练

    # total_batch个批次训练完成后，使用验证数据计算误差与准确率；验证集没有分批
    loss, acc = sess.run([loss_function, accuracy],
                         feed_dict={x: mnist.validation.images, y: mnist.validation.labels})
    # 打印训练过程中的详细信息
    if (epoch + 1) % display_step == 0:
        print("Train Epoch:", '%02d' % (epoch + 1), "Loss=", "{:.9f}".format(loss),
              " Accuracy=", "{:.4f}".format(acc))

#显示总运行时间
duration=time()-startTime
print("Train Finished takes:","{:.2f}".format(duration))

#评估模型
# 测试集
accu_test =  sess.run(accuracy,feed_dict={x: mnist.test.images, y: mnist.test.labels})
print("Test Accuracy:",accu_test)

# 验证集
accu_validation =  sess.run(accuracy,feed_dict={x: mnist.validation.images, y: mnist.validation.labels})
print("Test Accuracy:",accu_validation)

# 训练集
accu_train =  sess.run(accuracy,feed_dict={x: mnist.train.images, y: mnist.train.labels})
print("Test Accuracy:",accu_train)

#进行预测
# 由于pred预测结果是one-hot编码格式，所以需要转换为0~9数字
prediction_result = sess.run(tf.argmax(pred, 1),feed_dict={x: mnist.test.images})

# 查看预测结果中的前10项
print(prediction_result[0:10])

#定义可视化函数
def plot_images_labels_prediction(images,  # 图像列表
                                  labels,  # 标签列表
                                  prediction,  # 预测值列表
                                  index,  # 从第index个开始显示
                                  num=10):  # 缺省一次显示 10 幅
    fig = plt.gcf()  # 获取当前图表，Get Current Figure
    fig.set_size_inches(10, 12)  # 1英寸等于 2.54 cm
    if num > 25:
        num = 25  # 最多显示25个子图
    for i in range(0, num):
        ax = plt.subplot(5, 5, i + 1)  # 获取当前要处理的子图

        ax.imshow(np.reshape(images[index], (28, 28)),  # 显示第index个图像
                  cmap='binary')

        title = "label=" + str(np.argmax(labels[index]))  # 构建该图上要显示的title信息
        if len(prediction) > 0:
            title += ",predict=" + str(prediction[index])

        ax.set_title(title, fontsize=10)  # 显示图上的title信息
        ax.set_xticks([]);  # 不显示坐标轴
        ax.set_yticks([])
        index += 1
    plt.show()

#可视化测试
plot_images_labels_prediction(mnist.test.images,
                              mnist.test.labels,
                              prediction_result, 10, 25)


#找出预测错误

# #将预测结果和数据集结果进行比较，相同为True，不相同为False，并添加到数组中
compare_lists = prediction_result == np.argmax(mnist.test.labels, 1)
print(compare_lists)

#遍历数组找到错误集
err_lists = [i for i in range(len(compare_lists)) if compare_lists[i] == False]
print(err_lists, len(err_lists))

#定义输出错误分类的函数
def print_predict_errs(labels,  # 标签列表
                       prediction):  # 预测值列表
    count = 0
    compare_lists = (prediction == np.argmax(labels, 1))
    err_lists = [i for i in range(len(compare_lists)) if compare_lists[i] == False]
    for x in err_lists:
        print("index=" + str(x) +
              " 标签值=", np.argmax(labels[x]),
              "预测值=", prediction[x])
        count = count + 1
    print("总计:" + str(count))

#输出错误分类
print_predict_errs(labels=mnist.test.labels,
                   prediction=prediction_result)
#可视化错误
plot_images_labels_prediction(mnist.test.images,
                              mnist.test.labels,
                              prediction_result, 460, 10)

D:\PycharmProjects\12313\venv\Scripts\python.exe D:/PycharmProjects/12313/venv/wd.py
Extracting ./MNIST_data/train-images-idx3-ubyte.gz
WARNING:tensorflow:From D:/PycharmProjects/12313/venv/wd.py:8: read_data_sets (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use alternatives such as official/mnist/dataset.py from tensorflow/models.
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:260: maybe_download (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Please write your own downloading logic.
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:262: extract_images (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.data to implement this functionality.
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:267: extract_labels (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.data to implement this functionality.
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:110: dense_to_one_hot (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.one_hot on tensors.
Extracting ./MNIST_data/train-labels-idx1-ubyte.gz
Extracting ./MNIST_data/t10k-images-idx3-ubyte.gz
Extracting ./MNIST_data/t10k-labels-idx1-ubyte.gz
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:290: DataSet.__init__ (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use alternatives such as official/mnist/dataset.py from tensorflow/models.
WARNING:tensorflow:From C:\Users\86159\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
2020-10-30 20:05:53.215972: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Train Epoch: 01 Loss= 0.231269002  Accuracy= 0.9470
Train Epoch: 02 Loss= 0.123510331  Accuracy= 0.9564
Train Epoch: 03 Loss= 0.080938324  Accuracy= 0.9600
Train Epoch: 04 Loss= 0.065896586  Accuracy= 0.9622
Train Epoch: 05 Loss= 0.056072030  Accuracy= 0.9662
Train Epoch: 06 Loss= 0.056290332  Accuracy= 0.9656
Train Epoch: 07 Loss= 0.048462611  Accuracy= 0.9680
Train Epoch: 08 Loss= 0.051546317  Accuracy= 0.9658
Train Epoch: 09 Loss= 0.046421070  Accuracy= 0.9692
Train Epoch: 10 Loss= 0.045615450  Accuracy= 0.9734
Train Epoch: 11 Loss= 0.042802423  Accuracy= 0.9700
Train Epoch: 12 Loss= 0.044602182  Accuracy= 0.9746
Train Epoch: 13 Loss= 0.042120937  Accuracy= 0.9758
Train Epoch: 14 Loss= 0.047267921  Accuracy= 0.9732
Train Epoch: 15 Loss= 0.047390420  Accuracy= 0.9740
Train Epoch: 16 Loss= 0.048961017  Accuracy= 0.9726
Train Epoch: 17 Loss= 0.056563068  Accuracy= 0.9728
Train Epoch: 18 Loss= 0.060246896  Accuracy= 0.9720
Train Epoch: 19 Loss= 0.058890428  Accuracy= 0.9722
Train Epoch: 20 Loss= 0.056715332  Accuracy= 0.9762
Train Epoch: 21 Loss= 0.060174815  Accuracy= 0.9720
Train Epoch: 22 Loss= 0.052716885  Accuracy= 0.9744
Train Epoch: 23 Loss= 0.057576232  Accuracy= 0.9760
Train Epoch: 24 Loss= 0.063401639  Accuracy= 0.9764
Train Epoch: 25 Loss= 0.068671562  Accuracy= 0.9754
Train Epoch: 26 Loss= 0.065926589  Accuracy= 0.9748
Train Epoch: 27 Loss= 0.060092147  Accuracy= 0.9776
Train Epoch: 28 Loss= 0.069129013  Accuracy= 0.9710
Train Epoch: 29 Loss= 0.071569331  Accuracy= 0.9756
Train Epoch: 30 Loss= 0.070138879  Accuracy= 0.9760
Train Epoch: 31 Loss= 0.068267249  Accuracy= 0.9760
Train Epoch: 32 Loss= 0.078763261  Accuracy= 0.9736
Train Epoch: 33 Loss= 0.083575115  Accuracy= 0.9748
Train Epoch: 34 Loss= 0.078616537  Accuracy= 0.9764
Train Epoch: 35 Loss= 0.072792031  Accuracy= 0.9760
Train Epoch: 36 Loss= 0.085316330  Accuracy= 0.9740
Train Epoch: 37 Loss= 0.075117990  Accuracy= 0.9762
Train Epoch: 38 Loss= 0.084839240  Accuracy= 0.9734
Train Epoch: 39 Loss= 0.087352283  Accuracy= 0.9746
Train Epoch: 40 Loss= 0.088541605  Accuracy= 0.9732
Train Finished takes: 100.99
Test Accuracy: 0.9732
Test Accuracy: 0.9732
Test Accuracy: 0.99707276
[7 2 1 0 4 1 4 9 5 9]
[ True  True  True ...  True  True  True]
[151, 247, 259, 290, 320, 321, 340, 381, 437, 445, 447, 448, 507, 582, 603, 610, 619, 659, 674, 691, 717, 726, 740, 846, 882, 950, 951, 956, 965, 1014, 1039, 1044, 1045, 1112, 1156, 1181, 1226, 1232, 1242, 1247, 1260, 1299, 1319, 1393, 1433, 1494, 1522, 1530, 1549, 1553, 1559, 1609, 1621, 1681, 1709, 1717, 1730, 1754, 1782, 1790, 1800, 1901, 1981, 1982, 2004, 2016, 2035, 2070, 2093, 2098, 2109, 2125, 2129, 2130, 2135, 2162, 2182, 2185, 2189, 2215, 2237, 2266, 2272, 2293, 2369, 2382, 2387, 2414, 2433, 2454, 2462, 2488, 2597, 2654, 2720, 2730, 2760, 2810, 2863, 2896, 2927, 2939, 2953, 2979, 2995, 3023, 3030, 3060, 3073, 3117, 3172, 3225, 3289, 3330, 3369, 3475, 3503, 3520, 3533, 3550, 3558, 3559, 3604, 3681, 3751, 3767, 3780, 3796, 3808, 3811, 3817, 3818, 3853, 3893, 3906, 3941, 3946, 3954, 3976, 3984, 3985, 4000, 4007, 4018, 4065, 4075, 4078, 4140, 4156, 4163, 4176, 4199, 4201, 4224, 4255, 4271, 4284, 4359, 4433, 4455, 4477, 4497, 4500, 4536, 4551, 4552, 4571, 4575, 4601, 4619, 4635, 4639, 4731, 4751, 4807, 4808, 4860, 4880, 4890, 4956, 4990, 5068, 5246, 5331, 5457, 5586, 5634, 5642, 5654, 5676, 5718, 5734, 5737, 5749, 5769, 5888, 5936, 5937, 5955, 5973, 6009, 6023, 6045, 6059, 6065, 6166, 6390, 6597, 6605, 6608, 6625, 6632, 6641, 6651, 6755, 6847, 6905, 7208, 7216, 7259, 7338, 7457, 7459, 7473, 7524, 7545, 7574, 7849, 7899, 8020, 8059, 8094, 8110, 8115, 8160, 8246, 8277, 8408, 8456, 8508, 8522, 8527, 9009, 9015, 9019, 9024, 9163, 9316, 9425, 9587, 9634, 9652, 9664, 9679, 9692, 9698, 9719, 9729, 9745, 9764, 9770, 9792, 9808, 9839, 9856, 9858, 9888, 9980] 268
index=151 标签值= 9 预测值= 8
index=247 标签值= 4 预测值= 2
index=259 标签值= 6 预测值= 0
index=290 标签值= 8 预测值= 5
index=320 标签值= 9 预测值= 8
index=321 标签值= 2 预测值= 7
index=340 标签值= 5 预测值= 3
index=381 标签值= 3 预测值= 7
index=437 标签值= 3 预测值= 8
index=445 标签值= 6 预测值= 0
index=447 标签值= 4 预测值= 9
index=448 标签值= 9 预测值= 8
index=507 标签值= 3 预测值= 5
index=582 标签值= 8 预测值= 2
index=603 标签值= 8 预测值= 5
index=610 标签值= 4 预测值= 6
index=619 标签值= 1 预测值= 8
index=659 标签值= 2 预测值= 3
index=674 标签值= 5 预测值= 3
index=691 标签值= 8 预测值= 4
index=717 标签值= 0 预测值= 6
index=726 标签值= 7 预测值= 3
index=740 标签值= 4 预测值= 7
index=846 标签值= 7 预测值= 9
index=882 标签值= 9 预测值= 4
index=950 标签值= 7 预测值= 2
index=951 标签值= 5 预测值= 4
index=956 标签值= 1 预测值= 3
index=965 标签值= 6 预测值= 0
index=1014 标签值= 6 预测值= 0
index=1039 标签值= 7 预测值= 8
index=1044 标签值= 6 预测值= 2
index=1045 标签值= 9 预测值= 1
index=1112 标签值= 4 预测值= 6
index=1156 标签值= 7 预测值= 3
index=1181 标签值= 6 预测值= 1
index=1226 标签值= 7 预测值= 2
index=1232 标签值= 9 预测值= 4
index=1242 标签值= 4 预测值= 9
index=1247 标签值= 9 预测值= 2
index=1260 标签值= 7 预测值= 1
index=1299 标签值= 5 预测值= 7
index=1319 标签值= 8 预测值= 3
index=1393 标签值= 5 预测值= 3
index=1433 标签值= 8 预测值= 1
index=1494 标签值= 7 预测值= 0
index=1522 标签值= 7 预测值= 9
index=1530 标签值= 8 预测值= 7
index=1549 标签值= 4 预测值= 6
index=1553 标签值= 9 预测值= 5
index=1559 标签值= 9 预测值= 3
index=1609 标签值= 2 预测值= 6
index=1621 标签值= 0 预测值= 6
index=1681 标签值= 3 预测值= 7
index=1709 标签值= 9 预测值= 3
index=1717 标签值= 8 预测值= 0
index=1730 标签值= 3 预测值= 8
index=1754 标签值= 7 预测值= 2
index=1782 标签值= 8 预测值= 9
index=1790 标签值= 2 预测值= 7
index=1800 标签值= 6 预测值= 2
index=1901 标签值= 9 预测值= 4
index=1981 标签值= 6 预测值= 9
index=1982 标签值= 6 预测值= 5
index=2004 标签值= 8 预测值= 9
index=2016 标签值= 7 预测值= 2
index=2035 标签值= 5 预测值= 3
index=2070 标签值= 7 预测值= 1
index=2093 标签值= 8 预测值= 1
index=2098 标签值= 2 预测值= 0
index=2109 标签值= 3 预测值= 8
index=2125 标签值= 5 预测值= 9
index=2129 标签值= 9 预测值= 2
index=2130 标签值= 4 预测值= 9
index=2135 标签值= 6 预测值= 1
index=2162 标签值= 5 预测值= 8
index=2182 标签值= 1 预测值= 2
index=2185 标签值= 0 预测值= 5
index=2189 标签值= 9 预测值= 1
index=2215 标签值= 6 预测值= 5
index=2237 标签值= 5 预测值= 6
index=2266 标签值= 1 预测值= 3
index=2272 标签值= 8 预测值= 0
index=2293 标签值= 9 预测值= 6
index=2369 标签值= 5 预测值= 3
index=2382 标签值= 8 预测值= 2
index=2387 标签值= 9 预测值= 1
index=2414 标签值= 9 预测值= 7
index=2433 标签值= 2 预测值= 1
index=2454 标签值= 6 预测值= 5
index=2462 标签值= 2 预测值= 0
index=2488 标签值= 2 预测值= 4
index=2597 标签值= 5 预测值= 3
index=2654 标签值= 6 预测值= 1
index=2720 标签值= 9 预测值= 4
index=2730 标签值= 7 预测值= 4
index=2760 标签值= 9 预测值= 4
index=2810 标签值= 5 预测值= 3
index=2863 标签值= 9 预测值= 4
index=2896 标签值= 8 预测值= 0
index=2927 标签值= 3 预测值= 2
index=2939 标签值= 9 预测值= 7
index=2953 标签值= 3 预测值= 5
index=2979 标签值= 9 预测值= 1
index=2995 标签值= 6 预测值= 5
index=3023 标签值= 8 预测值= 5
index=3030 标签值= 6 预测值= 8
index=3060 标签值= 9 预测值= 1
index=3073 标签值= 1 预测值= 2
index=3117 标签值= 5 预测值= 9
index=3172 标签值= 4 预测值= 9
index=3225 标签值= 7 预测值= 1
index=3289 标签值= 8 预测值= 9
index=3330 标签值= 2 预测值= 9
index=3369 标签值= 9 预测值= 1
index=3475 标签值= 3 预测值= 7
index=3503 标签值= 9 预测值= 1
index=3520 标签值= 6 预测值= 4
index=3533 标签值= 4 预测值= 9
index=3550 标签值= 6 预测值= 5
index=3558 标签值= 5 预测值= 0
index=3559 标签值= 8 预测值= 5
index=3604 标签值= 7 预测值= 0
index=3681 标签值= 2 预测值= 3
index=3751 标签值= 7 预测值= 2
index=3767 标签值= 7 预测值= 2
index=3780 标签值= 4 预测值= 6
index=3796 标签值= 2 预测值= 8
index=3808 标签值= 7 预测值= 8
index=3811 标签值= 2 预测值= 3
index=3817 标签值= 2 预测值= 9
index=3818 标签值= 0 预测值= 6
index=3853 标签值= 6 预测值= 0
index=3893 标签值= 5 预测值= 8
index=3906 标签值= 1 预测值= 3
index=3941 标签值= 4 预测值= 6
index=3946 标签值= 2 预测值= 8
index=3954 标签值= 8 预测值= 9
index=3976 标签值= 7 预测值= 1
index=3984 标签值= 9 预测值= 8
index=3985 标签值= 9 预测值= 4
index=4000 标签值= 9 预测值= 4
index=4007 标签值= 7 预测值= 9
index=4018 标签值= 3 预测值= 5
index=4065 标签值= 0 预测值= 9
index=4075 标签值= 8 预测值= 5
index=4078 标签值= 9 预测值= 7
index=4140 标签值= 8 预测值= 2
index=4156 标签值= 2 预测值= 8
index=4163 标签值= 9 预测值= 7
index=4176 标签值= 2 预测值= 5
index=4199 标签值= 7 预测值= 9
index=4201 标签值= 1 预测值= 7
index=4224 标签值= 9 预测值= 7
index=4255 标签值= 5 预测值= 3
index=4271 标签值= 5 预测值= 3
index=4284 标签值= 9 预测值= 5
index=4359 标签值= 5 预测值= 3
index=4433 标签值= 7 预测值= 2
index=4455 标签值= 8 预测值= 0
index=4477 标签值= 0 预测值= 6
index=4497 标签值= 8 预测值= 7
index=4500 标签值= 9 预测值= 1
index=4536 标签值= 6 预测值= 5
index=4551 标签值= 7 预测值= 4
index=4552 标签值= 3 预测值= 9
index=4571 标签值= 6 预测值= 2
index=4575 标签值= 4 预测值= 2
index=4601 标签值= 8 预测值= 4
index=4619 标签值= 6 预测值= 5
index=4635 标签值= 3 预测值= 5
index=4639 标签值= 8 预测值= 9
index=4731 标签值= 8 预测值= 7
index=4751 标签值= 4 预测值= 6
index=4807 标签值= 8 预测值= 3
index=4808 标签值= 3 预测值= 5
index=4860 标签值= 4 预测值= 9
index=4880 标签值= 0 预测值= 8
index=4890 标签值= 8 预测值= 3
index=4956 标签值= 8 预测值= 4
index=4990 标签值= 3 预测值= 2
index=5068 标签值= 4 预测值= 7
index=5246 标签值= 7 预测值= 2
index=5331 标签值= 1 预测值= 6
index=5457 标签值= 1 预测值= 2
index=5586 标签值= 8 预测值= 0
index=5634 标签值= 2 预测值= 3
index=5642 标签值= 1 预测值= 5
index=5654 标签值= 7 预测值= 2
index=5676 标签值= 4 预测值= 2
index=5718 标签值= 0 预测值= 5
index=5734 标签值= 3 预测值= 2
index=5737 标签值= 0 预测值= 9
index=5749 标签值= 8 预测值= 5
index=5769 标签值= 5 预测值= 8
index=5888 标签值= 4 预测值= 0
index=5936 标签值= 4 预测值= 9
index=5937 标签值= 5 预测值= 3
index=5955 标签值= 3 预测值= 8
index=5973 标签值= 3 预测值= 8
index=6009 标签值= 3 预测值= 5
index=6023 标签值= 3 预测值= 9
index=6045 标签值= 3 预测值= 8
index=6059 标签值= 3 预测值= 8
index=6065 标签值= 3 预测值= 8
index=6166 标签值= 9 预测值= 3
index=6390 标签值= 5 预测值= 8
index=6597 标签值= 0 预测值= 7
index=6605 标签值= 6 预测值= 5
index=6608 标签值= 9 预测值= 5
index=6625 标签值= 8 预测值= 4
index=6632 标签值= 9 预测值= 5
index=6641 标签值= 8 预测值= 5
index=6651 标签值= 0 预测值= 5
index=6755 标签值= 8 预测值= 9
index=6847 标签值= 6 预测值= 4
index=6905 标签值= 9 预测值= 8
index=7208 标签值= 8 预测值= 3
index=7216 标签值= 0 预测值= 3
index=7259 标签值= 8 预测值= 3
index=7338 标签值= 4 预测值= 1
index=7457 标签值= 2 预测值= 7
index=7459 标签值= 9 预测值= 5
index=7473 标签值= 4 预测值= 8
index=7524 标签值= 8 预测值= 9
index=7545 标签值= 8 预测值= 9
index=7574 标签值= 4 预测值= 1
index=7849 标签值= 3 预测值= 2
index=7899 标签值= 1 预测值= 8
index=8020 标签值= 1 预测值= 8
index=8059 标签值= 2 预测值= 1
index=8094 标签值= 2 预测值= 8
index=8110 标签值= 7 预测值= 3
index=8115 标签值= 3 预测值= 8
index=8160 标签值= 5 预测值= 3
index=8246 标签值= 3 预测值= 9
index=8277 标签值= 3 预测值= 9
index=8408 标签值= 8 预测值= 5
index=8456 标签值= 8 预测值= 0
index=8508 标签值= 3 预测值= 5
index=8522 标签值= 8 预测值= 6
index=8527 标签值= 4 预测值= 8
index=9009 标签值= 7 预测值= 2
index=9015 标签值= 7 预测值= 2
index=9019 标签值= 7 预测值= 2
index=9024 标签值= 7 预测值= 2
index=9163 标签值= 3 预测值= 2
index=9316 标签值= 8 预测值= 5
index=9425 标签值= 0 预测值= 6
index=9587 标签值= 9 预测值= 4
index=9634 标签值= 0 预测值= 1
index=9652 标签值= 7 预测值= 3
index=9664 标签值= 2 预测值= 7
index=9679 标签值= 6 预测值= 3
index=9692 标签值= 9 预测值= 7
index=9698 标签值= 6 预测值= 5
index=9719 标签值= 5 预测值= 3
index=9729 标签值= 5 预测值= 6
index=9745 标签值= 4 预测值= 2
index=9764 标签值= 4 预测值= 8
index=9770 标签值= 5 预测值= 3
index=9792 标签值= 4 预测值= 8
index=9808 标签值= 9 预测值= 4
index=9839 标签值= 2 预测值= 7
index=9856 标签值= 9 预测值= 5
index=9858 标签值= 6 预测值= 8
index=9888 标签值= 6 预测值= 0
index=9980 标签值= 2 预测值= 7
总计:268

Process finished with exit code 0

|
|