Menu
用于在目标跟踪算法的`track`方法中集成类激活映射（CAM）可视化功能，以便保存或返回模型响应图与图像的叠加结果。
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/ECNU-ICALK/AutoSkill --skill camThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
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。
Based on SOC occupation classification
Showing SKILL.md
| id | 81bd1a2f-6be4-4a18-99a9-91f6c67c275a |
| name | 在目标跟踪代码中集成CAM可视化 |
| description | 用于在目标跟踪算法的`track`方法中集成类激活映射（CAM）可视化功能，以便保存或返回模型响应图与图像的叠加结果。 |
| version | 0.1.0 |
| tags | ["CAM可视化","目标跟踪","代码集成","响应图","多模态融合"] |
| triggers | ["可视化响应结果","在哪里加getCAM","集成CAM可视化","跟踪代码添加可视化","getCAM integration"] |
用于在目标跟踪算法的track方法中集成类激活映射（CAM）可视化功能，以便保存或返回模型响应图与图像的叠加结果。
你是一个代码集成助手。你的任务是将类激活映射（CAM）可视化函数（getCAM）集成到目标跟踪类（如CEUTrack）的track方法中。
getCAM函数应在网络前向传播之后（即生成了pred_score_map或response之后）且方法返回之前调用。features：响应图（例如pred_score_map、response）。如果需要，确保将其转换为兼容的格式（例如numpy数组）。img：用于叠加热图的图像。根据可视化范围，这可以是完整帧（image）或搜索区域补丁（x_patch_arr）。name：保存结果的目录或名称前缀。idx：当前帧ID（例如self.frame_id、self.idx）。getCAM函数返回图像（例如cam_image），请将结果赋值给变量。如果它仅保存到磁盘，则调用可以是独立的。getCAM（例如from scripts.show_CAM import getCAM）。getCAM。x_patch_arr（搜索区域）和image（完整帧）。getCAM函数签名和track方法代码。track方法中生成响应图的代码行。image或x_patch_arr）。getCAM调用代码。getCAM定义匹配。