[深度学习框架] Keras上使用神经网络进行mnist分类

最新推荐文章于 2024-04-24 21:58:37 发布

原创最新推荐文章于 2024-04-24 21:58:37 发布 · 4.2k 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#keras #深度学习框架

深度学习专栏收录该内容

12 篇文章

订阅专栏

本文介绍了一个使用Keras构建的简单神经网络模型，该模型用于识别MNIST数据集中的手写数字。文章展示了从数据预处理到模型训练及评估的全过程，并采用RMSprop作为优化器。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# coding: utf-8
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.optimizers import RMSprop
np.random.seed(1337)


# download the mnist
(X_train, Y_train), (X_test, Y_test) = mnist.load_data()

# data pre-processing
X_train = X_train.reshape(X_train.shape[0], -1)/255
X_test = X_test.reshape(X_test.shape[0], -1)/255
Y_train = np_utils.to_categorical(Y_train, 10)
Y_test = np_utils.to_categorical(Y_test, 10)

# build neural network
model = Sequential([
    Dense(32, input_dim=784),
    Activation('relu'),
    Dense(10),
    Activation('softmax')
])

# define optimizer
rmsprop = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)

# add metrics to get more results you want to see
model.compile(loss='categorical_crossentropy', optimizer=rmsprop, metrics=['accuracy'])

# training
print 'Training'
model.fit(X_train, Y_train, epochs=2, batch_size=32)

# testing
print 'Testing'
loss, accuracy = model.evaluate(X_test, Y_test)
print 'loss, accuracy: ', (loss, accuracy)