القائمة
针对TensorFlow训练代码进行内存泄漏修复，包括优化数据管道、添加每轮结束后的垃圾回收回调以及修正ModelCheckpoint配置。
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/ECNU-ICALK/AutoSkill --skill tensorflowيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
استنادا إلى تصنيف SOC المهني
Manage personal local Agent Skill files as an installable skill manager. Proactively and periodically detect reusable user-specific, team-specific, or broadly reusable skill material during or after meaningful sessions; run non-blocking extraction checks; offer candidate skill titles or accept a user-supplied topic when extraction direction is ambiguous; preserve the appropriate output language; search local and external skill ecosystems for similar skills; score candidates by evidence, recurrence, personal value, and portability; fully draft proposed skills or diffs before asking for approval; then, after explicit user approval, discard, improve, merge, or create `SKILL.md` folders.
布置结构化家庭作业，引导求助者记录现实互动事件、自动思维及情绪反应，并设计简易验证行动（如主动询问、观察反证），用于检验投射性认知偏差。适用于已识别出具体非理性信念（如‘别人肯定不喜欢我’）且情绪稳定者。
结构化8次CBT咨询流程，按评估性会谈→咨询性会谈→巩固性会谈三阶段推进，整合悬搁接地技术与认知行为策略，专用于强迫症伴轻度抑郁状态、具自省力与作业执行力的成年来访者。
عرض SKILL.md
| id | c3ae29fb-1604-4e89-b1ab-3b2956586c69 |
| name | TensorFlow 训练代码内存优化与修复 |
| description | 针对TensorFlow训练代码进行内存泄漏修复，包括优化数据管道、添加每轮结束后的垃圾回收回调以及修正ModelCheckpoint配置。 |
| version | 0.1.0 |
| tags | ["tensorflow","内存泄漏","代码优化","gc.collect","训练回调"] |
| triggers | ["修改tensorflow代码解决内存泄漏","在每个epoch结束后调用gc.collect","修复ModelCheckpoint的max_to_keep参数","优化tf.data数据管道"] |
针对TensorFlow训练代码进行内存泄漏修复，包括优化数据管道、添加每轮结束后的垃圾回收回调以及修正ModelCheckpoint配置。
You are a TensorFlow code optimization expert. Your task is to refactor user-provided TensorFlow training code to address memory leaks and configuration errors based on specific requirements.
tf.data.Dataset creation logic. Ensure batching is handled efficiently and avoid operations that cause excessive memory retention (e.g., unnecessary caching or prefetching if memory is tight).MemoryCleanupCallback) that overrides on_epoch_end to call gc.collect(). This ensures garbage collection happens after every epoch, not just at the end of training.ModelCheckpoint callbacks. Remove invalid parameters such as max_to_keep (which is specific to tf.train.CheckpointManager and not ModelCheckpoint).model.fit() callbacks list.gc.collect() only after model.fit() finishes; it must be inside a callback triggered per epoch.max_to_keep in ModelCheckpoint.