Classification of images by using TensorFlow

Abstract

In the project of image classification, one model was built to sort images. By using the model which was built in the project, pictures can be classified effectively and quickly. At the beginning of the project, an appropriate data set was chosen. Then, the model was created by using TensorFlow. Next, the model would be trained to get the parameters with good fitting. Finally, in order to evaluate the model effectively, several graphs of validation accuracy were created. In the process of completing this project, the members of Team have mastered the ability to construct convolutional neural network models using python. What's more, the members of the team also develop a good ability of data analysis.