界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
效率与协作 · SKILL.md

vision-multimodal

vision-multimodal

【效率与协作】Operate AutoTrain Advanced image classification, image regression, object detection, and VLM app/API/config workflows.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

技能说明

GitHub

name: vision-multimodal description: "Operate AutoTrain Advanced image classification, image regression, object detection, and VLM app/API/config workflows." disable-model-invocation: true metadata: disco-role: operating parent-skill: autotrain-advanced license: Apache 2.0

AutoTrain vision and multimodal workflows

Use this sub-skill for image classification, image regression/scoring, object detection, and VLM dataset/task flows.

Supported entry points

  • autotrain image-classification --help
  • autotrain image-regression --help
  • autotrain object-detection --help
  • YAML aliases: image-classification, image-regression, image-scoring, object-detection, image-object-detection, vlm:captioning, vlm:vqa
  • App/API task keys: image-classification, image-regression, image-object-detection, vlm:captioning, vlm:vqa

Important: there is no top-level autotrain vlm command in this checkout. Route VLM through the app/API/config flow.

Data-layout summary

TaskLocal layout
image classificationdirectory with at least two class subfolders; each class folder has at least five jpg/jpeg/png files and no extra files/subfolders
image regressiondirectory with at least five images plus metadata.jsonl containing file_name and target
object detectiondirectory with at least five images plus metadata.jsonl containing file_name and objects
VLMdirectory with at least five images plus metadata.jsonl containing file_name and all mapped text/prompt columns

Use scripts/validate_vision_data.py for bounded local layout checks.

Safe validation sequence

  1. Inspect relevant CLI help with the root inspect_cli.py helper.
  2. Validate YAML with the root validate_config.py helper.
  3. Validate local image folders/metadata with scripts/validate_vision_data.py.
  4. If VLM or UI/API parameters are involved, use ../app-backends/ to inspect app/API task params and backend auth.
  5. Launch only after data layout, model id, task alias, backend, and Hub credentials are explicit.

References

  • references/workflows.md — route patterns and launch/check examples.
  • references/data-formats.md — local folder and metadata schemas.
  • references/troubleshooting.md — image file counts, metadata parsing, VLM route, and backend issues.
我的收藏