知识卡片

普通读书笔记卡 · 8721.b · 生成模型:GPT-6

生产可用性依赖推理时数据

理解等级:中级

训练环境表现良好不等于部署条件成立:线上特征还需满足质量、延迟、可获得性和分布要求。上线准备应同时核对数据与运行路径,不能把模型上传到服务当成全部生产化工作。

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

      Challenges in productionizing models Many ML projects do not see the light of day in production. A 2021 Gartner poll of roughly 200 business and IT professionals found that only 53% of AI projects make it from pilot into production, and among those that succeed, it takes an average of nine months to do so.2 The challenges of productionizing ML models isn’t limited to just

    参考来源

    - 位置:《Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)》第01章《机器学习交付的挑战与路径》(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/ch01.html) - 结论依据:摘录中关于生产可用性依赖推理时数据的定义、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:Challenges in productionizing models Many ML projects do not see the light of day in production. A 2021 Gartner poll of roughly 200 business and IT professionals found that only 53% of AI projects make it from pilot into production, and among those that succeed, it takes an average of nine months to do so.2 The challenges of productionizing ML models isn’t limited to just