1. What is TensorFlow?
The origin of the name TensorFlow is the flow of tensors in a computational graph, as shown in the figure. In addition to automatically helping you find gradients, it also provides a variety of common operations (OP, i.e., nodes of the graph), common loss functions, and optimization algorithms.
- TensorFlow is an open-source software library for high-performance numerical computing. With its flexible architecture, users can easily deploy computing jobs to multiple platforms (CPUs, GPUs, TPUs) and devices (desktops, server clusters, mobile devices, edge devices, etc.).https://www.tensorflow.org/tutorials/?hl=zh-cnwww.tensorflow.org/tutorials/?hl=zh-cn(opens new window)
- TensorFlow is an open-source machine learning library for research and production. TensorFlow provides a variety of APIs for beginners and experts to develop in desktop, mobile, web, and cloud environments.
- TensorFlow is calculated using data flow graphs, so first we have to create a data flow graph, and then put our data (data in the form of tensors) in the data flow graph for calculation. Nodes represent mathematical operations in a graph, and edges represent arrays of multidimensional data that are interconnected between nodes, i.e., tensors. When training a…