基于卷积神经网络的手写数字识别代码及数据集
时间: 2023-09-16 10:12:00 浏览: 48
以下是基于卷积神经网络(CNN)的手写数字识别代码及数据集:
代码:
```python
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
# 设置模型参数
batch_size = 128
num_classes = 10
epochs = 12
# 输入图像的维度
img_rows, img_cols = 28, 28
# 加载 MNIST 数据集
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# 根据 Keras 后端设置图像维度的顺序,将输入数据的形状进行转换
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)
# 将图像像素值转换为浮点数,并进行归一化
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
# 将标签转换为 one-hot 编码
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
# 定义模型结构
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
# 编译模型
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
# 训练模型
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
# 评估模型
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
```
数据集:
MNIST 数据集是一个常用的手写数字识别数据集,包含 60000 个训练样本和 10000 个测试样本,每个样本都是一个 28x28 的灰度图像。可以通过 Keras 中的 `mnist.load_data()` 函数获取该数据集。
```python
from keras.datasets import mnist
# 加载 MNIST 数据集
(x_train, y_train), (x_test, y_test) = mnist.load_data()
```
注意:在使用 Keras 加载 MNIST 数据集时,数据集已经被分为训练集和测试集,并且进行了预处理(将像素值归一化到 [0, 1] 区间)。因此,不需要进行额外的预处理。