基于Keras搭建用于MNIST手写数字识别的CNN

最新推荐文章于 2023-08-28 16:23:47 发布

fxlou

最新推荐文章于 2023-08-28 16:23:47 发布

阅读量968

点赞数 1

分类专栏： keras 文章标签： python keras

本文链接：https://blog.youkuaiyun.com/fxlou/article/details/79189896

版权

本文档介绍了如何使用Keras库搭建一个卷积神经网络（CNN）来识别MNIST数据集的手写数字。内容涵盖Sequential模型、backend概念、数据预处理、Dense层、Activation层、Dropout层、Flatten层、Conv2D层、MaxPooling2D层的使用，以及模型编译、训练和评估的步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

说明
以下代码引自Keras的Github网站：

https://github.com/keras-team/keras/blob/master/examples/mnist_cnn.py

为了学习Keras 平台进行深度学习建模的过程，我加入了一些备注和说明。
代码

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# 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)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3,

最低0.47元/天解锁文章