MNIST Data Set Recognition Research based on TensorFlow Framework

Jie Liu ； Chenghua Fu

《International Core Journal of Engineering》 7卷2期 (2021/02) Pp. 410-414

https://doi.org/10.6919/ICJE.202102_7(2).0055

摘要

TensorFlow is one of the current mainstream frameworks for deep learning. As an end-to-end open source machine learning platform, it has a comprehensive and flexible ecosystem, including rich libraries and community resources. Based on the TensorFlow framework, this paper uses MNIST as the data set to build a model and make prediction, and obtains a convolutional neural network (CNN) to recognize grayscale handwritten numbers. At the same time, compared with traditional classification, the research shows that the CNN has a higher recognition rate for images, and the experimental results show that the recognition rate of the CNN reaches 99.38%.

關鍵字

Deep Learning ； Tensorflow ； Softmax Classification ； MNIST ； Convolutional Neural Network

參考文獻

Lecun, Y, L. Bottou, Gradient-based learning applied to document recognition. Proceedings of the IEEE, Vol. 86(1998) No. 11, p. 2278-2324.

K. He, Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society.

Krizhevsky, A., Sutskever, I. & Hinton, G. ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Vol.25(2012), 1106–1114

Simonyan K, Zisserman A . Very Deep Convolutional Networks for Large-Scale Image Recognition [EB/OL]. (2015-04-10). http://arxiv.org/abs/1409.1556.

J. H. Li, TensorFlow of Deep Learning: Introduction, Principle and Advanced Actual Combat. Beijing: Mechanical Industry Press, 2018.