摘要
Keras是以TensorFlow+Theano为后端的深度学习框架,相比于TensorFlow,Keras更加灵活快速。相比于经典的神经网络模型,卷积神经网络对图像的识别效率更高。文章基于Keras建立深度学习模型,以MNIST数据集为例,构建卷积神经网络,训练模型并进行预测,得到的MNIST数据集识别模型,达到了99.23%的识别正确率。
Keras is a deep learning framework based on TensorFlow+Theano.Keras is more flexible and faster than Tensorflow.Convolutional neural networks are more efficient at identifying images than classical neural network models.This paper builds a deep learning model based on Keras.Taking the MNIST data set as an example,constructing a convolutional neural network,training the model and predicting it,the obtained MNIST dataset recognition model achieves a recognition accuracy rate of 99.23%.
作者
郭梦洁
杨梦卓
马京九
GUO Mengjie;YANG Mengzhuo;MA Jingjiu(Anhui University,Hefei 230601,China;Yangtze University,Wuhan 430100,China)
出处
《现代信息科技》
2019年第14期18-19,23,共3页
Modern Information Technology
