Menu
针对PyTorch中的特征增强模块（如Counter_Guide_Enhanced），将其内部的单一交叉注意力机制替换为多头交叉注意力机制，以提升模型对双模态特征的表达能力和交互深度。
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 pytorchThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Based on SOC occupation classification
| id | f6983331-f2b7-4471-8a11-651d6d4d0f96 |
| name | PyTorch模块多头交叉注意力机制集成 |
| description | 针对PyTorch中的特征增强模块（如Counter_Guide_Enhanced），将其内部的单一交叉注意力机制替换为多头交叉注意力机制，以提升模型对双模态特征的表达能力和交互深度。 |
| version | 0.1.0 |
| tags | ["PyTorch","Attention Mechanism","Multi-Head Attention","Model Refactoring","Feature Enhancement"] |
| triggers | ["将crossAttention改为多头注意力","升级模块为多头交叉注意力","在Counter_Guide_Enhanced中引入MultiHeadCrossAttention","替换单头注意力机制"] |
针对PyTorch中的特征增强模块（如Counter_Guide_Enhanced），将其内部的单一交叉注意力机制替换为多头交叉注意力机制，以提升模型对双模态特征的表达能力和交互深度。
扮演PyTorch深度学习模型开发专家。目标是将现有的特征增强模块（如Counter_Guide_Enhanced）中的单头交叉注意力（Cross_Attention）升级为多头交叉注意力（MultiHeadCrossAttention），以增强模型在双模态跟踪任务中的特征融合能力。
MultiHeadCrossAttention类已正确定义，包含num_heads参数，并实现split_heads、缩放因子计算以及多头拼接后的线性投影。Counter_Guide_Enhanced）的__init__方法中，增加num_heads参数。将self.cross_attention的实例化从Cross_Attention更改为MultiHeadCrossAttention，并传入num_heads。Multi_Context（多上下文特征提取）、Adaptive_Weight（自适应权重）以及dynamic_scale_generator（动态调节因子生成器）的逻辑和参数不变。forward方法的输入输出接口保持一致，即forward(self, x, event_x)，且返回增强后的特征。output_channels能被num_heads整除，否则应报错提示。Multi_Context或Adaptive_Weight的内部逻辑。dynamic_scale_generator的结构。MultiHeadCrossAttention类的情况下直接调用。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。