huggingface-vision-trainer

77 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.

By huggingface/skills (GitHub) · media · 11,321 stars · scanned at commit 25910b3

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, T…

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README.

Found in 5 places.

skills/huggingface-vision-trainer/SKILL.md, line 31uv run scripts/dataset_inspector.py --dataset username/dataset-name --split train
skills/huggingface-vision-trainer/SKILL.md, line 93uv run scripts/dataset_inspector.py --dataset username/dataset-name --split train
skills/huggingface-vision-trainer/references/reliability_principles.md, line 206subprocess.run([...], check=True, capture_output=True)

Show 2 more

skills/huggingface-vision-trainer/references/reliability_principles.md, line 210result = subprocess.run(
skills/huggingface-vision-trainer/references/reliability_principles.md, line 219except subprocess.CalledProcessError as e:

Downloads and installs other software

The author does not mention this.

Found in 5 places.

skills/huggingface-vision-trainer/references/finetune_sam2_trainer.md, line 7!pip install -q transformers datasets monai trackio
skills/huggingface-vision-trainer/references/image_classification_training_notebook.md, line 26pip install transformers datasets evaluate accelerate pillow torchvision scikit-learn trackio
skills/huggingface-vision-trainer/references/object_detection_training_notebook.md, line 32pip install -q datasets transformers accelerate timm trackio

Show 2 more

skills/huggingface-vision-trainer/references/object_detection_training_notebook.md, line 33pip install -q -U albumentations>=1.4.5 torchmetrics pycocotools
skills/huggingface-vision-trainer/scripts/object_detection_training.py, line 55require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/object-detection/requirements.txt")

Connects to the internet

The author does not mention this. Expected for a media skill.

Found in 4 places.

skills/huggingface-vision-trainer/references/object_detection_training_notebook.md, line 646>>> image = Image.open(requests.get(url, stream=True).raw)
skills/huggingface-vision-trainer/scripts/dataset_inspector.py, line 26import urllib.request
skills/huggingface-vision-trainer/scripts/dataset_inspector.py, line 37parser.add_argument("--samples", type=int, default=5, help="Number of samples to fetch (default: 5)")

Show 1 more

skills/huggingface-vision-trainer/scripts/dataset_inspector.py, line 45with urllib.request.urlopen(url, timeout=10) as response:

Safer alternatives

Low-risk skills in the same category (media) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'huggingface-vision-trainer' ] || [ -L ~/.agents/skills/'huggingface-vision-trainer' ]; then echo 'A skill folder named huggingface-vision-trainer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/huggingface/skills' "$d" && git -C "$d" checkout --quiet '25910b3d0ba31a2ba102f901cdc9e008c278a69c' -- 'skills/huggingface-vision-trainer' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/huggingface-vision-trainer' ~/.agents/skills/'huggingface-vision-trainer' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'huggingface-vision-trainer' ~/.claude/skills/'huggingface-vision-trainer' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for huggingface/skills shows the score of its lowest-scoring skill.

SkillTrust badge for huggingface/skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/huggingface/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/huggingface/skills/)

Score history

Date	Version	Score
2026-11-08	`25910b3`	77
2026-11-06	`25910b3`	67