一个简单的MNIST神经网络

1.导入所需模块：

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers
from multiprocessing import pool
from operator import mod
from pickletools import optimize

2.准备数据：

num_classes = 10
input_shape = (28,28,1)

(x_train, y_train),(x_test, y_test) = keras.datasets.mnist.load_data()

x_train = x_train.astype("float32")/255
x_test  = x_test.astype("float32")/255

#make sure images have shape(28,28,1)
x_train = np.expand_dims(x_train, -1)
x_test = np.expand_dims(x_test, -1)

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test  = keras.utils.to_categorical(y_test, num_classes)

3.建立训练模型

model = keras.Sequential(
    [
        keras.Input(shape=input_shape),
        layers.Conv2D(32,kernel_size=(3,3),activation="relu"),
        layers.MaxPooling2D(pool_size=(2,2)),
        layers.Conv2D(64,kernel_size=(3,3),activation="relu"),
        layers.MaxPooling2D(pool_size=(2,2)),
        layers.Flatten(),
        layers.Dropout(0.5),
        layers.Dense(num_classes,activation="softmax"),
    ]
)

model.summary()

4.开始训练

batch_size = 128
epochs = 15

model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
model.fit(x_train,y_train,batch_size=batch_size, epochs=epochs,validation_split= 0.1)

5.评价模型

score = model.evaluate(x_test, y_test, verbose=0)
print("Test loss:", score[0])
print("Test accuracy:",score[1])

6.训练结果