学习python的一些基础语法知识，后按照百度平台给的课程照抄完成了第一个数字识别的模型，下面是详细的文档链接和讲解
https://aistudio.baidu.com/aistudio/projectdetail/150131?_origin=newbie
中间需要注意的是，它给出的图片是不存在的，需要自己去下载一张图片
我用了一张7的图片保存为jfif文件，照样可以实现，最后预测的数据和结果如下：
[[[[ 0.16078436 0.23921573 0.3176471 0.3176471 0.30196083
0.30196083 0.28627455 0.2941177 0.28627455 0.28627455
0.27843142 0.27058828 0.26274514 0.26274514 0.24705887
0.22352946 0.22352946 0.23921573 0.24705887 0.24705887
0.26274514 0.254902 0.23921573 0.20784318 0.21568632
0.19215691 0.12941182 -0.2235294 ]
[-0.10588235 0.39607847 0.07450986 0.12156868 0.09803927
0.10588241 0.12941182 0.11372554 0.09019613 0.11372554
0.10588241 0.09019613 0.07450986 0.082353 0.06666672
0.06666672 0.04313731 0.04313731 0.05882359 0.05098045
0.05098045 0.05882359 0.0196079 0.01176476 0.02745104
-0.06666666 0.45882356 -0.01960784]
[ 0.05098045 0.3803922 -0.41960782 -0.31764704 -0.34117645
-0.3333333 -0.34117645 -0.3333333 -0.30196077 -0.3098039
-0.3098039 -0.31764704 -0.31764704 -0.30196077 -0.3098039
-0.3098039 -0.3098039 -0.3098039 -0.3098039 -0.31764704
-0.3333333 -0.3333333 -0.3333333 -0.32549018 -0.32549018
-0.4352941 0.33333337 0.00392163]
[ 0.02745104 0.4039216 -0.3333333 -0.24705881 -0.23921567
-0.23921567 -0.23137254 -0.23137254 -0.2235294 -0.23137254
-0.23921567 -0.23137254 -0.2235294 -0.2235294 -0.2235294
-0.21568626 -0.19999999 -0.21568626 -0.23137254 -0.21568626
-0.21568626 -0.23137254 -0.24705881 -0.25490195 -0.25490195
-0.372549 0.34901965 0.00392163]
[ 0.05098045 0.4039216 -0.32549018 -0.25490195 -0.2862745
-0.27843136 -0.25490195 -0.25490195 -0.27058822 -0.24705881
-0.23137254 -0.23137254 -0.21568626 -0.20784312 -0.2235294
-0.23137254 -0.23921567 -0.2235294 -0.23137254 -0.23137254
-0.2235294 -0.23137254 -0.24705881 -0.23137254 -0.2235294
-0.3490196 0.35686278 0.01176476]
[ 0.03529418 0.4039216 -0.31764704 -0.24705881 -0.27058822
-0.27058822 -0.26274508 -0.26274508 -0.24705881 -0.23921567
-0.24705881 -0.25490195 -0.25490195 -0.25490195 -0.25490195
-0.23137254 -0.20784312 -0.2235294 -0.23137254 -0.23921567
-0.23137254 -0.23137254 -0.23137254 -0.24705881 -0.23921567
-0.3490196 0.3411765 0.0196079 ]
[ 0.07450986 0.4039216 -0.3960784 -0.32549018 -0.32549018
-0.29411763 -0.29411763 -0.27843136 -0.25490195 -0.24705881
-0.19999999 -0.19215685 -0.1607843 -0.09803921 -0.11372548
-0.17647058 -0.2862745 -0.23137254 -0.2235294 -0.24705881
-0.23921567 -0.23137254 -0.23921567 -0.23137254 -0.23137254
-0.3490196 0.41176474 -0.01960784]
[-0.09803921 0.41960788 0.06666672 0.12941182 0.12156868
0.12941182 0.16078436 0.15294123 0.1686275 0.17647064
0.20000005 0.20784318 0.20784318 0.19215691 0.23921573
0.3803922 0.3176471 -0.21568626 -0.2235294 -0.23137254
-0.23137254 -0.23921567 -0.23921567 -0.23137254 -0.27843136
-0.09803921 0.4431373 -0.11372548]
[ 0.04313731 0.20000005 0.3411765 0.3411765 0.36470592
0.3803922 0.4039216 0.427451 0.4666667 0.49803925
0.52156866 0.56078434 0.5921569 0.62352943 0.60784316
-0.04313725 0.58431375 -0.17647058 -0.23921567 -0.2235294
-0.2235294 -0.23137254 -0.23921567 -0.2235294 -0.35686272
0.36470592 0.0196079 0.5058824 ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
1. 1. 1. 1. 0.3176471
0.13725495 0.34901965 -0.3098039 -0.20784312 -0.21568626
-0.23137254 -0.2235294 -0.23137254 -0.29411763 -0.05882353
0.41960788 -0.01960784 0.99215686]
[ 0.99215686 0.99215686 0.99215686 0.9843137 0.9843137
0.9843137 0.9843137 0.9843137 0.9843137 0.9843137
0.9843137 0.96862745 0.99215686 0.654902 -0.20784312
0.5686275 -0.15294117 -0.23921567 -0.2235294 -0.2235294
-0.21568626 -0.23921567 -0.20784312 -0.32549018 0.41960788
-0.01176471 0.60784316 1. ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
0.99215686 0.9843137 0.94509804 -0.14509803 0.41176474
0.10588241 -0.30196077 -0.20784312 -0.20784312 -0.23137254
-0.23921567 -0.23137254 -0.3098039 -0.03529412 0.3803922
-0.00392157 1. 0.9843137 ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
0.9843137 1. 0.20000005 0.1686275 0.32549024
-0.34117645 -0.2235294 -0.23137254 -0.2235294 -0.2235294
-0.23921567 -0.23137254 -0.3490196 0.43529415 -0.03529412
0.6313726 1. 0.9843137 ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 1. 0.9843137
1. 0.6 -0.04313725 0.49803925 -0.30196077
-0.24705881 -0.23921567 -0.23921567 -0.23921567 -0.23137254
-0.21568626 -0.30196077 0.00392163 0.37254906 0.03529418
1. 0.9764706 1. ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 0.99215686 0.9843137
0.9137255 -0.09803921 0.48235297 -0.11372548 -0.2862745
-0.23921567 -0.23921567 -0.23921567 -0.23137254 -0.23137254
-0.21568626 -0.3098039 0.45882356 -0.06666666 0.67058825
1. 0.9843137 1. ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 0.9843137 1.
0.14509809 0.23921573 0.18431377 -0.38039213 -0.23921567
-0.25490195 -0.25490195 -0.26274508 -0.26274508 -0.23137254
-0.3098039 0.05098045 0.34901965 0.07450986 1.
0.9843137 1. 1. ]
[ 1. 1. 1. 1. 1.
1. 1. 0.9843137 1. 0.5686275
-0.00392157 0.45882356 -0.3333333 -0.24705881 -0.25490195
-0.25490195 -0.25490195 -0.25490195 -0.25490195 -0.23921567
-0.30196077 0.47450984 -0.08235294 0.7254902 0.99215686
0.9843137 1. 1. ]
[ 1. 1. 1. 1. 1.
1. 0.99215686 0.9843137 0.8901961 -0.09803921
0.5058824 -0.12941176 -0.27843136 -0.23137254 -0.25490195
-0.24705881 -0.23921567 -0.23137254 -0.23137254 -0.3333333
0.082353 0.3176471 0.10588241 1. 0.9843137
1. 1. 1. ]
[ 1. 1. 1. 1. 1.
1. 0.9843137 1. 0.12941182 0.28627455
0.1686275 -0.3490196 -0.24705881 -0.23921567 -0.23921567
-0.23921567 -0.23921567 -0.24705881 -0.23137254 -0.29411763
0.4901961 -0.08235294 0.7647059 0.99215686 0.99215686
1. 1. 1. ]
[ 1. 1. 1. 1. 1.
0.9843137 1. 0.5294118 -0.02745098 0.427451
-0.34117645 -0.24705881 -0.24705881 -0.25490195 -0.2235294
-0.23921567 -0.23921567 -0.2235294 -0.3333333 0.12941182
0.27843142 0.15294123 1. 0.9764706 1.
1. 1. 1. ]
[ 1. 1. 1. 1. 0.99215686
0.99215686 0.8666667 -0.12156862 0.49803925 -0.17647058
-0.27843136 -0.23921567 -0.24705881 -0.23921567 -0.26274508
-0.25490195 -0.24705881 -0.23137254 -0.2862745 0.5058824
-0.09803921 0.8117647 0.99215686 0.99215686 1.
1. 1. 1. ]
[ 1. 1. 1. 1. 0.9764706
1. 0.09803927 0.30196083 0.13725495 -0.36470586
-0.25490195 -0.25490195 -0.25490195 -0.26274508 -0.24705881
-0.2235294 -0.2235294 -0.32549018 0.15294123 0.21568632
0.20000005 1. 0.9843137 1. 1.
1. 1. 1. ]
[ 1. 1. 1. 0.9843137 1.
0.4901961 0.01176476 0.4431373 -0.34117645 -0.24705881
-0.2862745 -0.25490195 -0.24705881 -0.26274508 -0.24705881
-0.23921567 -0.26274508 -0.2862745 0.49803925 -0.11372548
0.84313726 0.99215686 0.99215686 1. 1.
1. 1. 1. ]
[ 1. 1. 0.99215686 0.99215686 0.84313726
-0.1372549 0.5058824 -0.19999999 -0.30196077 -0.26274508
-0.26274508 -0.24705881 -0.25490195 -0.25490195 -0.26274508
-0.25490195 -0.372549 0.19215691 0.20000005 0.24705887
1. 0.9764706 1. 1. 1.
1. 1. 1. ]
[ 1. 1. 0.9764706 1. 0.05882359
0.33333337 0.12941182 -0.3490196 -0.25490195 -0.27843136
-0.27058822 -0.25490195 -0.24705881 -0.24705881 -0.24705881
-0.27843136 -0.26274508 0.47450984 -0.11372548 0.8901961
0.99215686 0.99215686 1. 1. 1.
1. 1. 1. ]
[ 1. 0.9843137 1. 0.4901961 0.04313731
0.37254906 -0.40392154 -0.30196077 -0.32549018 -0.3333333
-0.34117645 -0.3333333 -0.34117645 -0.35686272 -0.3490196
-0.46666664 0.20784318 0.16078436 0.30980396 1.
0.9843137 1. 1. 1. 1.
1. 1. 1. ]
[ 0.99215686 1. 0.77254903 -0.32549018 0.32549024
0.23921573 0.12941182 0.14509809 0.12156868 0.10588241
0.10588241 0.082353 0.05882359 0.05882359 0.03529418
0.03529418 0.45098042 -0.09019607 0.92156863 0.99215686
0.99215686 1. 1. 1. 1.
1. 1. 1. ]
[ 0.99215686 1. 0.6392157 0.26274514 0.30196083
0.3176471 0.2941177 0.27058828 0.27058828 0.2313726
0.21568632 0.22352946 0.19215691 0.20000005 0.19215691
0.21568632 -0.1607843 0.39607847 1. 0.9764706
1. 1. 1. 1. 1.
1. 1. 1. ]]]]
该图片的预测结果的label为: 7
接下来我用一张包含两个数字的图片试一下：
经过预处理的图片如下很明显是16
但是最后跑出来的结果是错误的，识别为3
[[[[ 1. 1. 1. 1. 1.
1. 0.9843137 1. 1. 1.
1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
0.99215686 0.99215686 1. 1. 1.
1. 1. 1. ]
[ 1. 1. 1. 1. 1.
0.99215686 1. 1. 1. 1.
1. 1. 1. 1. 1.
1. 1. 1. 0.9764706 1.
1. 1. 0.99215686 0.9843137 1.
1. 1. 1. ]
[ 1. 1. 0.9764706 0.9764706 0.96862745
1. 0.7176471 0.9843137 1. 1.
1. 1. 1. 1. 1.
1. 1. 0.99215686 1. 1.
0.7411765 0.7647059 1. 1. 0.99215686
1. 1. 1. ]
[ 1. 1. 1. 1. 1.
0.5529412 -0.5137255 0.9843137 1. 1.
1. 1. 1. 1. 1.
0.99215686 0.99215686 1. 0.11372554 -0.5294118
-0.4823529 -0.5921569 -0.5294118 0.64705884 1.
0.9843137 1. 1. ]
[ 1. 0.9372549 0.4431373 0.38823533 0.04313731
-0.85882354 -0.62352943 1. 0.99215686 1.
1. 1. 1. 1. 0.99215686
0.9764706 1. -0.38039213 -0.5686275 0.62352943
0.9764706 0.92156863 -0.67058825 -0.81960785 0.81960785
0.99215686 0.99215686 1. ]
[ 1. 0.8745098 -0.16862744 -0.21568626 -0.6627451
-1. -0.54509807 1. 0.99215686 1.
1. 1. 1. 1. 0.9764706
1. -0.11372548 -0.7647059 0.9843137 1.
0.9764706 1. -0.3333333 -1. 0.06666672
1. 0.96862745 1. ]
[ 1. 1. 1. 1. 0.92156863
-0.92941177 -0.6 1. 0.99215686 1.
1. 1. 1. 0.9843137 1.
0.67058825 -1. 0.5137255 1. 0.9607843
0.9764706 0.99215686 -0.38039213 -1. 0.17647064
1. 0.96862745 1. ]
[ 1. 1. 0.96862745 0.96862745 0.9607843
-0.8666667 -0.62352943 1. 0.99215686 1.
1. 1. 1. 0.9764706 1.
-0.27843136 -0.8666667 0.9764706 0.99215686 0.99215686
0.99215686 1. 0.75686276 0.35686278 0.94509804
1. 0.99215686 1. ]
[ 1. 1. 0.99215686 1. 0.94509804
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.99215686 1. 0.92156863
-0.9137255 -0.3960784 1. 0.9764706 1.
1. 1. 1. 1. 1.
1. 1. 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9764706 1. 0.5529412
-1. -0.04313725 1. 0.94509804 0.9764706
0.9843137 0.9764706 0.9607843 0.96862745 0.99215686
1. 1. 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.96862745 1. 0.15294123
-0.99215686 0.17647064 0.9843137 1. 1.
1. 1. 1. 1. 1.
1. 1. 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.96862745 1. -0.14509803
-1. 0.30196083 1. 0.54509807 -0.3333333
-0.5921569 -0.41960782 0.254902 0.99215686 1.
0.99215686 1. 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9764706 1. -0.3490196
-1. 0.5294118 0.2941177 -0.94509804 -0.38823527
-0.12156862 -0.60784316 -1. -0.35686272 0.9607843
0.9843137 0.99215686 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9843137 1. -0.52156866
-1. 0.082353 -0.7254902 0.5764706 1.
1. 1. -0.17647058 -1. 0.13725495
1. 0.9764706 1. ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.99215686 1. -0.5921569
-1. -0.85882354 0.4666667 1. 0.9529412
0.9529412 1. 0.9137255 -0.8352941 -0.77254903
0.94509804 0.99215686 0.99215686]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.99215686 1. -0.54509807
-1. -0.41176468 1. 0.96862745 1.
1. 0.96862745 1. -0.2235294 -1.
0.5764706 1. 0.9764706 ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9843137 1. -0.5058824
-1. 0.38823533 0.99215686 0.96862745 1.
1. 0.96862745 0.99215686 0.17647064 -0.99215686
0.21568632 1. 0.96862745]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9843137 1. -0.42745095
-1. 0.427451 1. 0.9764706 1.
1. 0.96862745 1. 0.30980396 -1.
0.03529418 1. 0.96862745]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.96862745 1. -0.1607843
-1. 0.30196083 1. 0.9764706 1.
1. 0.96862745 1. 0.3176471 -1.
0.04313731 1. 0.96862745]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.96862745 1. 0.11372554
-0.99215686 0.07450986 0.99215686 0.96862745 1.
1. 0.96862745 1. 0.254902 -1.
0.17647064 1. 0.96862745]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8745098 -0.62352943 1. 0.99215686 1.
1. 1. 0.9764706 1. 0.5686275
-1. -0.3098039 1. 0.9764706 1.
1. 0.96862745 1. 0.09803927 -1.
0.43529415 1. 0.9764706 ]
[ 1. 1. 0.99215686 1. 0.9529412
-0.8666667 -0.6313726 0.99215686 0.99215686 1.
1. 1. 0.99215686 1. 0.92941177
-0.81960785 -0.8352941 0.92941177 0.99215686 0.99215686
1. 0.96862745 0.99215686 -0.21568626 -0.99215686
0.8117647 1. 0.9843137 ]
[ 1. 1. 0.9607843 0.96862745 0.94509804
-0.8980392 -0.6 1. 0.9607843 0.96862745
1. 1. 1. 0.96862745 1.
0.05098045 -1. 0.27843142 1. 0.94509804
0.9764706 0.96862745 1. -0.79607844 -0.4352941
1. 0.9764706 1. ]
[ 1. 1. 1. 1. 0.69411767
-0.96862745 -0.78039217 0.9372549 1. 1.
1. 1. 1. 0.99215686 0.9843137
0.8980392 -0.7176471 -0.8901961 0.8039216 1.
1. 1. 0.1686275 -0.9764706 0.70980394
0.99215686 0.9843137 1. ]
[ 1. 0.8980392 0.07450986 -0.01176471 -0.78039217
-1. -1. -0.69411767 -0.01176471 0.12156868
0.9372549 1. 1. 1. 0.9843137
1. 0.70980394 -0.64705884 -0.8352941 0.10588241
0.32549024 -0.1607843 -0.7647059 0.4901961 1.
0.9843137 1. 1. ]
[ 1. 0.9137255 0.18431377 0.15294123 0.23921573
0.2941177 0.30196083 0.22352946 0.15294123 0.22352946
0.94509804 1. 1. 1. 1.
0.9843137 1. 0.94509804 0.2313726 -0.25490195
-0.26274508 0.03529418 0.8509804 1. 0.9843137
1. 1. 1. ]
[ 1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
1. 1. 1. 1. 1.
1. 0.9843137 1. 1. 1.
1. 1. 1. 0.9843137 1.
1. 1. 1. ]
[ 1. 1. 0.96862745 0.96862745 0.96862745
0.96862745 0.96862745 0.96862745 0.96862745 0.96862745
1. 1. 1. 1. 1.
1. 1. 0.99215686 0.96862745 0.96862745
0.96862745 0.96862745 0.99215686 1. 1.
1. 1. 1. ]]]]
该图片的预测结果的label为: 3
Process finished with exit code 0
当然这个模型本身的建立就是用于识别一个数字，所以在接下来如果有空，我会尝试改写成识别所有的数字，再次仅作为一个纪念