# self / torch / none

> General SOP for common requests related to self, torch, none.

- Skill: `ecnu-icalk/self-torch-none` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ecnu-icalk/self-torch-none`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ecnu-icalk/self-torch-none/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ECNU-ICALK (https://skillmd.com/u/ecnu-icalk)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/ecnu-icalk/self-torch-none

---


# self / torch / none

General SOP for common requests related to self, torch, none.

## Prompt

Follow this SOP (replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>):
1) from . import BaseActor
2) from lib.utils.misc import NestedTensor
3) from lib.utils.box_ops import box_cxcywh_to_xyxy, box_xywh_to_xyxy
4) import torch
5) from lib.utils.merge import merge_template_search
6) from ...utils.heapmap_utils import generate_heatmap
7) from ...utils.ce_utils import generate_mask_cond, adjust_keep_rate
8) class CEUTrackActor(BaseActor
9) Actor for training CEUTrack models
10) def __init__(self, net, objective, loss_weight, settings, cfg=None

For each step, include: action, checks, and failure rollback/fallback plan.
Output format: for each step number, provide status/result and what to do next.

## Triggers

- Use when the user asks for a process or checklist.
- Use when you want to reuse a previously mentioned method/SOP.

## Examples

### Example 1

Input:

  Break this into best-practice, executable steps.