Research and Implementation of CNN Based on TensorFlow. Issue 3 (April 2019)

• Record Type: Journal Article
• Authors: Yu, Liang; Li, Binbin; Jiao, Bin
• Is Part Of: IOP conference series. Volume 490:Issue 3(2019)
• Publication Date: 2019-04
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/490/4/042022
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: TensorFlow is Google's open source machine learning and deep learning framework, which is convenient and flexible to build the current mainstream deep learning model. Convolutional neural network is a classical model of deep learning, the advantage lies in its powerful feature extraction capabilities of convolutional blocks. Based on the TensorFlow platform, a convolutional neural network model with two-convolution-layers was built. The model was trained and tested with the MNIST data set. The test accuracy rate could reach 99.15%, and compared with the rate of 98.69% with only one-convolution-layer model, which shows that the two-convolution-layers convolutional neural network model has a better ability of feature extraction and classification decision-making.