Agent SkillsML · ModelsOfficial

huggingface-vision-trainer

skills/huggingface-vision-trainer · huggingface/skills · by Hugging Face

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.

Repo stars
11,351
huggingface/skills · 2026-11-15
Last commit
2026-03-23
to this skill folder
Files
12
5 scripts
License
Apache-2.0
repository license

Source · GitHub API and the SKILL.md frontmatter, read 2026-11-15 · stars are for the whole huggingface/skills repository

Ready-to-paste · from the repository README and the skill folder

# Copy this skill folder into your personal Claude Code skills
git clone --depth 1 --filter=blob:none --sparse --branch main https://github.com/huggingface/skills.git /tmp/huggingface-vision-trainer-src
git -C /tmp/huggingface-vision-trainer-src sparse-checkout set skills/huggingface-vision-trainer
mkdir -p ~/.claude/skills
cp -R /tmp/huggingface-vision-trainer-src/skills/huggingface-vision-trainer ~/.claude/skills/huggingface-vision-trainer
Claude Code reads skills from ~/.claude/skills/<name>/SKILL.md.Claude Code docs
Ecosystem · Agent Skills

Skill repositories from other publishers in the open Agent Skills format (agentskills.io) · a folder with a SKILL.md plus optional scripts and resources, read by any client that supports the format.

Files · 12
SKILL.mdreferences/finetune_sam2_trainer.mdreferences/hub_saving.mdreferences/image_classification_training_notebook.mdreferences/object_detection_training_notebook.mdreferences/reliability_principles.mdreferences/timm_trainer.mdscripts/dataset_inspector.pyscripts/estimate_cost.pyscripts/image_classification_training.pyscripts/object_detection_training.pyscripts/sam_segmentation_training.py
Scripts · 5
scripts/dataset_inspector.pyscripts/estimate_cost.pyscripts/image_classification_training.pyscripts/object_detection_training.pyscripts/sam_segmentation_training.py

Same repository · huggingface/skills · latest commit first

Drop into your README · links to this skill page

huggingface-vision-trainer · listed on BenchGecko
[![huggingface-vision-trainer · listed on BenchGecko](https://benchgecko.ai/badge/skill/huggingface-vision-trainer.svg)](https://benchgecko.ai/skills/huggingface-vision-trainer)
The badge shows the skill ecosystem label · BenchGecko does not rate skills.

Built from the GitHub data above

What is huggingface-vision-trainer?

huggingface-vision-trainer is a Agent Skills agent skill by Hugging Face, in the skills/huggingface-vision-trainer folder of the huggingface/skills repository (BenchGecko category: ML · Models). Its SKILL.md describes it as: 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.

Where does this data come from?

From GitHub, read 2026-11-15: the name and description from the SKILL.md frontmatter, 12 files from the repository tree, the last commit to the folder on 2026-03-23, and 11,351 stars for the whole huggingface/skills repository. BenchGecko does not rate skills.

How do I install huggingface-vision-trainer?

Copy the skills/huggingface-vision-trainer folder into ~/.claude/skills/ for Claude Code, use the command from the huggingface/skills README, or point any client that supports the Agent Skills format at the folder. Ready-to-paste snippets are above.

Is huggingface-vision-trainer official?

huggingface-vision-trainer is published in huggingface/skills, a repository owned by the Hugging Face organization on GitHub.

Keep exploring the BenchGecko graph