Huggingface Vision Trainer

What This Skill Does

The Hugging Face Vision Trainer skill enables users to train object detection, image classification, and SAM/SAM2 segmentation models on cloud GPUs via Hugging Face Jobs. It eliminates the need for local GPU setup, automatically saving results to the Hugging Face Hub. This skill is ideal for users looking to fine-tune vision models with custom datasets and ensure persistent storage of trained models.

When to Use

• Fine-tune object detection models on cloud GPUs.
• Fine-tune image classification models.
• Fine-tune SAM/SAM2 models for segmentation.
• Train bounding-box detectors on custom datasets.
• Train image classifiers on custom datasets.
• Run vision training jobs on Hugging Face Jobs.

Key Features

• Supports object detection, image classification, and segmentation.
• Utilizes managed cloud GPUs via Hugging Face Jobs.
• Automatically saves trained models to the Hugging Face Hub.
• Compatible with D-FINE, RT-DETR v2, DETR, and YOLOS.
• Supports timm: Mobile NetV3, Mobile ViT, Res Net, ViT/DINOv3.
• Enables training with custom datasets.

Manual Installation

When to Use This Skill

Use this skill when users want to: Fine-tune object detection models (D-FINE, RT-DETR v2, DETR, YOLOS) on cloud GPUs or local Fine-tune image classification models (timm: Mobile NetV3, Mobile ViT, Res Net, ViT/DINOv3, or any Transformers classifier) on cloud GPUs or local Fine-tune SAM or SAM2 models for segmentation / image matting using bbox or point prompts Train bounding-box detectors on custom datasets Train image classifiers on custom datasets Train segmentation models on custom mask datasets with prompts Run vision training jobs on Hugging Face Jobs infrastructure Ensure trained vision models are permanently saved to the Hub