简体中文 / [English]


TensorFlow Learning Diary-3 Basic Concepts

 

This article is currently an experimental machine translation and may contain errors. If anything is unclear, please refer to the original Chinese version. I am continuously working to improve the translation.

Concept of Tensor

  • scalar: 1.3
  • vector: [1.3], [1.3, 2.5, 3.1, …]
  • matrix: [[1,2], [1, 3], [3, 5]]
  • tensor: rank > 2

In programming, broadly speaking, any data with dimensionality (≥ 0) can be called a Tensor. However, we usually refer to 0-dimensional data as scalars, and data with dimensionality > 1 as Tensors. (Slightly different from the mathematical definition—but to be honest, I never fully grasped the mathematical version anyway.)

I think a Tensor can be roughly understood as a multi-dimensional array.

TensorFlow

You can think of it as forming a “flow” by performing computations across different Tensors—hence the name TensorFlow.

The rest of the basic concepts will be learned through hands-on coding. I’ve uploaded them to GitHub.

Link: https://github.com/lyc8503/TensorFlow-study

This article is licensed under the CC BY-NC-SA 4.0 license.

Author: lyc8503, Article link: https://blog.lyc8503.net/en/post/tensorflow-3-basic/
If this article was helpful or interesting to you, consider buy me a coffee¬_¬
Feel free to comment in English below o/