【摘要】 卷积神经网络是在多层神经网络的基础上发展起来的主要用于图像分类和识别的一种深度学习方法.本文设计了1个4层的卷积神经网络,其中包括3个卷积层和1个softmax输出层,并且在Fashion-MNIST数据集上完成了网络的训练和测试.测试结果表明本文设计的卷积神经网络模型可以有效地实现服饰图像的分类.更多还原

【Abstract】 Convolution neural network( CNN) is a kind of deep learning method based on multilayer neural network,which is mainly used for image classification and recognition. A four-layer convolutional neural network that includes three convolutional layers and a softmax output layer was designed in this paper,and the network training and testing was completed on the Fashion-MNIST data set. The test results show that the convolutional neural network model designed in this paper can classify clothing images effectively.更多还原