这篇是《python深度学习》中的代码,我会以后慢慢把注释、笔记添加上来
import keras
import tensorflow as tf
from keras.models import Sequential#顺序结构
from keras.layers import Dense#全连接层
from keras.optimizers import SGD
from keras.datasets import mnist
from keras.utils import np_utils
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
from keras.datasets import mnist##数据加载
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
from keras import models##网络架构
from keras import layers
network = models.Sequential()
network.add(layers.Dense(512, activation = 'relu', input_shape = (28 * 28, )))
network.add(layers.Dense(10, activation = 'softmax'))
network.compile(optimizer = 'rmsprop',
loss = 'categorical_crossentropy',
metrics = ['accuracy'])##编译步骤
train_images = train_images.reshape((60000, 28 * 28))##准备图像数据
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255
from keras.utils import to_categorical##准备标签
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
network.fit(train_images, train_labels, epochs = 5, batch_size = 128)##训练网络
test_loss, test_acc = network.evaluate(test_images, test_labels)
本文介绍了使用Python深度学习框架Keras实现的MNIST手写数字识别模型。通过构建一个包含两个全连接层的神经网络,对MNIST数据集进行训练和测试,实现了98%以上的准确率。文章详细展示了数据预处理、网络架构搭建、模型编译、训练及评估的全过程。
&spm=1001.2101.3001.5002&articleId=104879084&d=1&t=3&u=c3d2a2b453b34802988ab33c5011ef6d)

被折叠的 条评论
为什么被折叠?



