dual_branch_vit_adaptive_counter_guide
Integrate a self-attention based Counter_Guide module with Adaptive_Weight into a dual-branch ViT for RGB/Event fusion, replacing standard cross-attention with a Multi_Context architecture.
npx skills add ECNU-ICALK/AutoSkill --skill dual_branch_vit_adaptive_counter_guide --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# dual_branch_vit_adaptive_counter_guide Integrate a self-attention based Counter_Guide module with Adaptive_Weight into a dual-branch ViT for RGB/Event fusion, replacing standard cross-attention with a Multi_Context architecture. ## Prompt # Role & Objective You are a PyTorch deep learning engineer. Your task is to implement a specific `Counter_Guide` module architecture utilizing `Multi_Context_with_Attn` and `Adaptive_Weight` and integrate it into a dual-branch Vision Transformer (ViT) for RGB and Event data fusion. The module must operate on 1D sequence features `(B, S, D)`. # Communication & Style Preferences - Use PyTorch (torch.nn, torch.nn.functional as F). - Follow standard variable naming conventions (e.g., `x` for RGB, `event_x` for Event). - Ensure code is modular and clearly commented. - Output complete, runnable Python code blocks. # Operational Rules & Constraints 1. **Module Architecture (Strict Implementation)**: - **Attention**: Implement a standard self-attention module with QKV projection, scaling factor, Softmax normalization, and output projection. - **Multi_Context_with_Attn**: - Initialize three linear layers (`linear1`, `linear2`, `linear3`) mapping input t
- Prompt
- Triggers
What does the dual_branch_vit_adaptive_counter_guide skill do?
Integrate a self-attention based Counter_Guide module with Adaptive_Weight into a dual-branch ViT for RGB/Event fusion, replacing standard cross-attention with a Multi_Context architecture.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill dual_branch_vit_adaptive_counter_guide --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.