keras卷积神经网络识别手写体

最新推荐文章于 2024-11-29 10:16:26 发布

翻译最新推荐文章于 2024-11-29 10:16:26 发布 · 381 阅读

文章标签：

#代码

keras学习专栏收录该内容

4 篇文章

订阅专栏

本文介绍了一种使用Keras库构建的深度学习模型，该模型利用卷积神经网络（CNN）对MNIST数据集的手写数字进行识别。模型包含多个卷积层、池化层和全连接层，并使用了Dropout防止过拟合。经过训练，模型在测试集上取得了良好的准确率。

from keras.datasets import mnist
from keras.utils import np_utils
import numpy as np
np.random.seed(10);

(x_Train,y_Train),(x_Test,y_Test)=mnist.load_data();
print("done");
x_Train4D=x_Train.reshape(x_Train.shape[0],28,28,1).astype('float32');
x_Test4D=x_Test.reshape(x_Test.shape[0],28,28,-1).astype('float32');

x_Train4D_normalize=x_Train4D/255;
x_Test4D_normalize=x_Test4D/255;

y_TrainOneHot=np_utils.to_categorical(y_Train);
y_TestOneHot=np_utils.to_categorical(y_Test);

from keras.models import Sequential
from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPooling2D

model=Sequential();
model.add(Conv2D(filters=16,kernel_size=(5,5),padding='same',input_shape=(28,28,1),activation='relu'));
model.add(MaxPooling2D(pool_size=(2,2)));
model.add(Conv2D(filters=36,kernel_size=(5,5),padding="same",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(10,activation='softmax'));

print(model.summary());

model.compile(loss="categorical_crossentropy",optimizer="adam",metrics=['accuracy']);
train_history=model.fit(x=x_Train4D_normalize,y=y_TrainOneHot,batch_size=300,validation_split=0.2,epochs=10,verbose=1);

scores=model.evaluate(x_Test4D_normalize,y_TestOneHot);
print(scores[1]);

prediction=model.predict_classes(x_Test4D_normalize);
print(prediction);

# 显示混淆矩阵
import pandas as pd
crosstab=pd.crosstab(y_Test,prediction,rownames=['label'],colnames=['prediction']);
print(crosstab);