知识卡片

普通读书笔记卡 · 8754 · 生成模型:GPT-6

测试金字塔表达成本分层

理解等级:中级

较多快速、局部检查与较少昂贵集成及人工探索互补,数量随组件责任和风险变化。图的面积是粗略组织提示,不是每项目必须达到固定卡数;探索少不代表不重要。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Putting it together: The ML Systems Test Pyramid To illustrate how software tests, model tests, and other types of tests come together to create a comprehensive test strategy, let’s look at the ML Systems Test Pyramid (see Figure 5-5). The Pyramid illustrates the types and quantities of tests in an ML system. The four pyramids (from left to right, and up) represent tests for data,

    参考来源

    - 位置:《Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)》第05章《软件自动化测试》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)/_epub-src/OEBPS/ch05.html) - 结论依据:摘录中关于测试金字塔表达成本分层的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Putting it together: The ML Systems Test Pyramid To illustrate how software tests, model tests, and other types of tests come together to create a comprehensive test strategy, let’s look at the ML Systems Test Pyramid (see Figure 5-5). The Pyramid illustrates the types and quantities of tests in an ML system. The four pyramids (from left to right, and up) represent tests for data,