概念
别名：tensors
机器学习中按形状组织的数字结构，是模型处理数据的基本单元。
已跟踪 3 条高相关材料
最近变化
2026-06-02 · 张量是机器学习模型处理数据的核心结构，用于表示标量、向量、矩阵和高维数组。
为什么值得关注
Tensor 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
What Are Tensors?
Hugging Face · 7.5 分
张量是机器学习模型处理数据的基础结构，它将文本、图像、音频等现实世界输入转换为数字矩阵进行计算，最终输出有用结果。张量本质上是按形状组织的数字，包括标量（0D）、向量（1D）、矩阵（2D）和高维数组。
CPU vs GPU vs TPU
ByteByteGo · 7.5 分
CPU, GPU, and TPU are optimized for different computation types: CPU handles general-purpose tasks with branching logic, GPU excels at para...
What Are Tensors?
Hugging Face · 7 分
张量是机器学习中组织数字的基本结构，用于将文本、图像和音频等现实世界数据转换为模型可处理的数值形式，实现从输入到输出的完整数据流。
已收录 3 条与 Tensor 相关的内容，按评分排序。
Tensors are the core data structure in machine learning that convert real-world inputs like text, images, and audio into numerical matrices for computation, producing meaningful outputs. They are simply numbers organized by shape, including scalars (0D), vectors (1D), matrices (2D), and higher-dimensional arrays.
入选理由：张量是机器学习模型处理数据的核心结构，用于表示标量、向量、矩阵和高维数组。
CPU, GPU, and TPU are optimized for different computation types: CPU handles general-purpose tasks with branching logic, GPU excels at parallel math operations like matrix multiplication, and TPU is specialized for machine learning tensor operations, guiding hardware selection for AI workloads.
入选理由：CPU has few powerful cores optimized for general-purpose tasks like web servers and databases with branching logic.
Tensors are fundamental structures in machine learning that organize numbers, enabling models to process real-world data like text, images, and audio by converting them into numerical forms for the complete input-to-output data flow.
入选理由：机器学习模型通过张量处理数据，张量是按形状组织的数字，标量为0D、向量为1D、矩阵为2D。
