C RADIOv2 G

🚀 RADIO Image Feature Extraction Model

This model is designed for visual feature extraction, generating image embeddings that can be utilized by downstream models for tasks like image classification.

🚀 Quick Start

This model can generate image embeddings for downstream applications. Here's a basic example of how to use it:

import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor

hf_repo = "nvidia/C-RADIOv2-g"

image_processor = CLIPImageProcessor.from_pretrained(hf_repo)
model = AutoModel.from_pretrained(hf_repo, trust_remote_code=True)
model.eval().cuda()

image = Image.open('./assets/radio.png').convert('RGB')
pixel_values = image_processor(images=image, return_tensors='pt', do_resize=True).pixel_values
pixel_values = pixel_values.cuda()

summary, features = model(pixel_values)

✨ Features

• Multiple Sizes: C - RADIOv2 models are available in multiple sizes, including Base (90M parameters), Large (320M parameters), Huge (653M parameters), and Gigantic (1.1B parameters).
• Enhanced Training: C - RADIOv2 was trained for 1M steps (400k more steps than v1), using inverse frequency sampling for data balancing and PHI Standardization for teacher distribution balancing.
• Commercial Use: This model is ready for commercial/non - commercial use.

📦 Installation

To use this model, you need to install the transformers library. You can install it using the following command:

pip install transformers

💻 Usage Examples

Basic Usage

import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor

hf_repo = "nvidia/C-RADIOv2-g"

image_processor = CLIPImageProcessor.from_pretrained(hf_repo)
model = AutoModel.from_pretrained(hf_repo, trust_remote_code=True)
model.eval().cuda()

image = Image.open('./assets/radio.png').convert('RGB')
pixel_values = image_processor(images=image, return_tensors='pt', do_resize=True).pixel_values
pixel_values = pixel_values.cuda()

summary, features = model(pixel_values)

Advanced Usage

from einops import rearrange
spatial_features = rearrange(spatial_features, 'b (h w) d -> b d h w', h=x.shape[-2] // patch_size, w=x.shape[-1] // patch_size)

📚 Documentation

Model Overview

[Github] [CVPR 2025] [CVPR 2024]

Description

This model performs visual feature extraction. For instance, RADIO generates image embeddings that can be used by a downstream model to classify images.

Deployment Geography

Global.

Use Case

The embeddings generated by this model are expected to be used by a downstream application, such as image - level understanding (image classification, curation, etc.), dense processing (semantic segmentation, depth estimation, etc.), and integration into a Vision - Language Model.

Release Date

Huggingface: 03/26/2025 via RADIO Collection of Models.

References

• [CVPR 2025] RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models
• [CVPR 2024] AM - RADIO: Agglomerative Vision Foundation Model - Reduce All Domains Into One

Model Architecture

Input

Output

Software Integration

Model Version(s)

• C - RADIOv2 - B (90M parameters).
• C - RADIOv2 - L (320M parameters).
• C - RADIOv2 - H (653M parameters).
• C - RADIOv2 - G (1.8B parameters).

Links:

• https://huggingface.co/nvidia/C - RADIOv2 - B
• https://huggingface.co/nvidia/C - RADIOv2 - L
• https://huggingface.co/nvidia/C - RADIOv2 - H
• https://huggingface.co/nvidia/C - RADIOv2 - g

Training and Evaluation Datasets

Training Dataset

• Dataset Name: NV - CC - Img - Text - Dataset
• Data Collection Method: Automated
• Labeling Method: Not Applicable (no labels are needed)
• Properties: 700 Million Images

Evaluation Dataset

• Link: ImageNet
• Data Collection Method: Automated
• Labeling Method: Human
• Properties: This dataset spans 1000 object classes and contains 1,281,167 training images, 50,000 validation images and 100,000 test images.

Inference

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and has established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with the terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards below.

Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en - us/support/submit - security - vulnerability/).

Bias

Explainability

Privacy

Safety

📄 License

Use of this model is governed by the [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia - open - model - license - agreement - june - 2024.pdf).