// fetch failed
Couldn't render the SKILL.md content here right now. You can view the raw markdown or open the source folder on GitHub.
AI/MLopenai
huggingface-vision-trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
- Stars
- 1,305
- Source
- openai/plugins
- Updated
- 2026-05-30
- Slug
- openai--plugins--vision-trainer
// install — copy + paste into any project
mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/openai/plugins/HEAD/plugins/hugging-face/skills/vision-trainer/SKILL.md -o .claude/skills/vision-trainer.mdDrops the SKILL.md into .claude/skills/vision-trainer.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.