hugging-face-vision-trainer 是做什麼的?
使用 Hugging Face Transformers 在 Hugging Face Jobs 上訓練和微調視覺模型,支援物件偵測 (D-FINE、RT-DETR v2、DETR、YOLOS)、影像分類 (timm 模型 — MobileNetV3、MobileViT、ResNet、ViT/DINOv3 — 以及任何 Transformers 分類器) 和 SAM/SAM2 分割。
使用 Hugging Face Transformers 在 Hugging Face Jobs 上訓練和微調視覺模型,支援物件偵測、影像分類和 SAM/SAM2 分割。
此技能專為開發者和 AI 代理設計,提供一個統一的介面,用於在 Hugging Face 平台上訓練和微調各種視覺模型。它支援多種電腦視覺任務:物件偵測(包括 D-FINE、RT-DETR v2、DETR 和 YOLOS)、影像分類(支援 timm 模型如 MobileNetV3、MobileViT、ResNet、ViT/DINOv3 以及任何 Transformers 分類器)以及 SAM/SAM2 分割。透過整合 Hugging Face Jobs,此技能可讓使用者無需手動管理基礎架構,即可大規模啟動訓練工作。其核心價值在於簡化設定流程、提供可自訂的訓練參數(如學習率、批次大小和時期數),並自動處理資料集轉換和模型保存。此技能可在支援 CLI 和 API 呼叫的 AI 代理平台(如 Claude Code、Cursor 或 Codex)中順暢運作,對於需要快速迭代視覺模型的機器學習工程師和研究人員來說是不可或缺的工具。
npx skills add https://github.com/dhar174/DeskBuddy/tree/main/.agents/skills/hugging-face-vision-trainer使用 Hugging Face Transformers 在 Hugging Face Jobs 上訓練和微調視覺模型,支援物件偵測 (D-FINE、RT-DETR v2、DETR、YOLOS)、影像分類 (timm 模型 — MobileNetV3、MobileViT、ResNet、ViT/DINOv3 — 以及任何 Transformers 分類器) 和 SAM/SAM2 分割。
This repo contains 2 individual skills — each has its own dedicated page.
Harden Docker/container images and runtime deployments with secure base images, non-root users, CVE scanning, SBOM/signing, seccomp/AppArmor, and Kubernetes pod security controls. Use for Dockerfile security reviews, container CVEs, image scanning, distroless images, or production hardening.
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".