# Hugging Face Vision Trainer

> Detection/SAM on HF Jobs GPUs

**Subcategory:** Hugging Face  
**License:** Apache-2.0  
**Source:** https://github.com/huggingface/skills/blob/main/skills/huggingface-vision-trainer/SKILL.md

---

## When it is useful

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.

## The Catch

detection/SAM on HF Jobs GPUs. Loud Catch: cloud-GPU costs apply.