6.1 卷积神经网络实例

CNN用于MNIST手写图片训练

qq_34047402

已于 2025-01-03 22:12:28 修改

阅读量449

点赞数 4

CC 4.0 BY-SA版权

分类专栏：人工智能文章标签： cnn 人工智能神经网络

于 2024-12-27 22:46:24 首次发布

本文链接：https://blog.csdn.net/qq_34047402/article/details/144778804

人工智能专栏收录该内容

23 篇文章

订阅专栏

1.层级如下：针对mnist手写28x28的图片，使用卷积神经网络进行训练：

卷积层1、池化层1、卷积层2、池化层2、Flatten层、隐含层、输出层。

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

mnist = tf.keras.datasets.mnist
(train_x,train_y),(test_x,test_y)=mnist.load_data()

train_x = train_x.reshape(60000,28,28,1)
test_x = test_x.reshape(10000,28,28,1)

X_train=tf.cast(train_x/255.0,tf.float32)
X_test = tf.cast(test_x/255.0, tf.float32)
Y_train =tf.cast(train_y,tf.int32)
Y_test = tf.cast(test_y,tf.int32)

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(16,kernel_size=(3,3),padding='same',activation=tf.nn.relu,input_shape=(28,28,1)),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Conv2D(32, kernel_size=(3, 3), padding='same', activation=tf.nn.relu),
    tf.keras.layers.MaxPool2D(pool_size=(2, 2)),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128,activation='relu'),
    tf.keras.layers.Dense(10,activation='softmax')
])
model.summary()
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['sparse_categorical_accuracy'])
history = model.fit(X_train,Y_train,batch_size=64,epochs=5,validation_split=0.2)
model.evaluate(X_test,Y_test,verbose=2)

y_pred = np.argmax(model.predict(X_test[0:4]),axis=1)
for i in range(4):
    plt.subplot(1,4,i+1)
    plt.axis('off')
    plt.imshow(test_x[i],cmap='gray')
    plt.title("y="+str(test_y[i])+"\n y_pred:"+str(y_pred[i]))
plt.show()
#model.save("testjuanji1.h5")