使用keras对mnist数据集做分类

最新推荐文章于 2025-06-27 16:49:43 发布

原创

最新推荐文章于 2025-06-27 16:49:43 发布 · 9.4k 阅读

9 ·

CC 4.0 BY-SA版权

文章标签：

#数据挖掘

本文通过Keras库演示了如何对MNIST数据集进行手写数字分类。代码详细展示了数据加载、预处理、构建神经网络模型、训练及评估过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

只贴代码：

原始数据集下载：http://yann.lecun.com/exdb/mnist/
代码说明：http://keras.io/getting-started/sequential-model-guide/#examples

"""
@version:
@author: vinsin
@license: Apache Licence
@software: PyCharm
@file: test_keras.py
@time: 16-7-19 下午4:53
"""

def load_mnist(path, kind='train'):
    """Load MNIST data from `path`"""
    labels_path = os.path.join(path, '%s-labels-idx1-ubyte' % kind)
    images_path = os.path.join(path, '%s-images-idx3-ubyte' % kind)
    with open(labels_path, 'rb') as lbpath:
        magic, n = struct.unpack('>II', lbpath.read(8))
        labels = np.fromfile(lbpath, dtype=np.uint8)
    with open(images_path, 'rb') as imgpath:
        magic, num, rows, cols = struct.unpack(">IIII", imgpath.read(16))
        images = np.fromfile(imgpath, dtype=np.uint8).reshape(len(labels), 784)
    return images, labels


X_train, y_train = load_mnist('../data', kind='train')
print('Rows: %d, columns: %d' % (X_train.shape[0], X_train.shape[1]))
X_test, y_test = load_mnist('../data', kind='t10k')
print('Rows: %d, columns: %d' % (X_test.shape[0], X_test.shape[1]))

import theano

theano.config.floatX = 'float32'
X_train = X_train.astype(theano.config.floatX)
X_test = X_test.astype(theano.config.floatX)

from keras.utils import np_utils

print('First 3 data: ', X_train[:3])
print('First 3 labels: ', y_train[:3])
y_train_ohe = np_utils.to_