Tensorflow2的MNIST数字识别实例及代码（jupyter长截图）

Tensorflow2的MNIST数字识别实例及代码（jupyter长截图）

 首先是个关于这个的长截图，包括结果以及代码：

使用长截图的方法，目前可行的是Chrome里F12，其他参照后面链接，edge的浏览器目前不可以

 

(1条消息) 新版Edge如何长截图_今天怎么又下雨的博客-CSDN博客_edge长截图https://blog.csdn.net/weixin_44122062/article/details/105855048另外可以使用QQ进行长截屏：

用电脑如何截长图，我懂你要的 - 知乎 (zhihu.com)https://zhuanlan.zhihu.com/p/358417947

 下面长截图为相应的代码及结论：

 

 需要代码及实际的步骤的可以参考下文：

 

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline 

print("Tensorflow version:", tf.__version__)

mnist =tf.keras.datasets.mnist
(train_images,train_labels),(test_images,test_labels)= mnist.load_data()

 

print("Train image shape:",train_images.shape,"Train label shape:",train_labels.shape)
print("Test image shape:",test_images.shape,"Test label shape:",test_labels.shape)

print("image data:",train_images[1])
print("train labels:",train_labels[1])

def plot_image(image):
    plt.imshow(image.reshape(28,28),cmap='binary')
    plt.show()

plot_image(train_images[1])

total_num =len(train_images)
print(total_num)
valid_split =0.2
train_num=int(total_num*(1-valid_split))
train_x =train_images[:train_num]
train_y =train_labels[:train_num]
valid_x=train_images[train_num:]
valid_y=train_labels[train_num:]
test_x = test_images
test_y =test_labels
valid_x.shape

进行数据的转换，转换为行向量：

train_x =train_x.reshape(-1,784)
valid_x =valid_x.reshape(-1,784)
test_x= test_x.reshape(-1,784)

进行归一化处理，因为像素是255，但对于实际自己数据需要使用：

train_x=tf.cast(train_x/255.0,tf.float32)
valid_x=tf.cast(valid_x/255.0,tf.float32)
test_x =tf.cast(test_x/255.0,tf.float32)

对于12列数据的一般数据归一化：

# 归一化处理
for i in range(12):
    x_data[:,i]=(x_data[:,i]-x_data[:,i].min())/(x_data[:,i].max()-x_data[:,i].min())

对label进行热码处理：

#对标签数据进行独热编码
train_y= tf.one_hot(train_y,depth=10)
valid_y= tf.one_hot(valid_y,depth=10)
test_y= tf.one_hot(test_y,depth=10)

build the model :

# build the model
def model(x,w,b):
    pred = tf.matmul(x,w)+b
    return tf.nn.softmax(pred)

#准备变量
W = tf.Variable(tf.random.normal([784,10],mean=0.0, stddev=1.0, dtype=tf.float32))
# don;t forget the random
B = tf.Variable(tf.zeros(10),dtype = tf.float32)
print(W)
print(B)

define the loss function:

def loss(x,y,w,b):
    pred =model(x,w,b)
    #loss_=tf.keras.losses.categorical_crossentroy(y_true=y,y_pred=pred)
    loss_= tf.keras.losses.categorical_crossentropy(y_true=y,y_pred=pred)
    return tf.reduce_mean(loss_)

#设置超参数
training_epochs =20
learning_rate =0.001
batch_size = 50  #批量训练一次的样本

def grad(x,y,w,b):
    with tf.GradientTape() as tape:
        loss_ =loss(x,y,w,b)
        return tape.gradient(loss_,[w,b])
  #返回梯度向量损失函数的，注意编程时的结构顺序

#选择优化器
optimizer = tf.keras.optimizers.Adam(learning_rate)
# help apply_gradients

def accuracy(x,y,w,b):
    pred =model(x,w,b)
    correct_prediction =tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
    return tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

 训练函数：

loss_list_train =[]
loss_list_valid =[]
acc_list_train =[]
acc_list_valid =[]
W_list=[]
B_list=[]
total_step = int (train_num/batch_size)
for epoch in range(training_epochs):
    for step in range(total_step):
        xs=train_x[step*batch_size:(step+1)*batch_size,:]
        ys=train_y[step*batch_size:(step+1)*batch_size]
        
        grads = grad(xs,ys,W,B) 
        #calculate the stiffness W B
        optimizer.apply_gradients(zip(grads,[W,B]))
    loss_train =loss(train_x,train_y,W,B).numpy()
    loss_valid =loss(valid_x,valid_y,W,B).numpy()
    acc_train =accuracy(train_x,train_y,W,B).numpy()
    acc_valid =accuracy(valid_x,valid_y,W,B).numpy()
    loss_list_train.append(loss_train)
    loss_list_valid.append(loss_valid)
    acc_list_train.append(acc_train)
    acc_list_valid.append(acc_valid)
    
    print("epoch={:3d},train_loss={:.4f},valid_loss={:.4f},train_acc={:.4f},valid_acc={:.4f}".format(epoch+1,loss_train,loss_valid,acc_train,acc_valid))

# graph
plt.xlabel("Epochs")
plt.ylabel("loss")
plt.plot(loss_list_train,'blue',label="Train_loss")
plt.plot(loss_list_valid,'red',label="Valid_loss")
plt.legend(loc=1)

# graph
plt.xlabel("Epochs")
plt.ylabel("acc")
plt.plot(acc_list_train,'blue',label="Train_acc")
plt.plot(acc_list_valid,'red',label="Valid_acc")
plt.legend(loc=1)

准确率结果：

acc_test = accuracy(test_x,test_y,W,B).numpy
print("Test accuracy:",acc_test)

数据的预测：

def predict(x, w, b):
    pred = model(x, w, b)
    result = tf.argmax(pred, 1).numpy()
    return result

pred_test=predict(test_x,W,B)
print(pred_test)

进行数字的可视化：

import matplotlib.pyplot as plt
import numpy as np

主要可视化代码，注意相应结构顺序：

def plot_images(images, labels, preds, index=0, num=10):  # 定义之后一次最多可以显示10张图片
    fig = plt.gcf()
    fig.set_size_inches(10, 4)  # 设置幕布的长和宽
    if num > 10:
        num = 10

    for i in range(0, num):
        ax = plt.subplot(2, 5, i + 1)  # 起到了规划图形之间的分布 同时也有i的循环来指定输出哪一幅图像
        # ax.imshow(np.reshape(images[index], (28, 28)), cmap='binary')
        tmp = images[index]
        tmp = tmp.reshape(28, 28)
        ax.imshow(tmp, cmap='binary')
        title = "label=" + str(labels[index])
        if len(preds) > 0:  # 因为有时只是想输出图像 可能会在没有预测值之前
            title += ",predict=" + str(preds[index])

        ax.set_title(title, fontsize=10)  # fontsize是字体大小
        ax.set_xticks([])
        ax.set_yticks([])
        index += 1
    plt.show()

最后显示命令：

plot_images(test_images,test_labels,pred_test,10,10)

总结：以上为完整的MNIST的TensorFlow2实现过程，相应的文件会单独上传