nvidia / C-RADIO

huggingface.co
Total runs: 2.0K
24-hour runs: 0
7-day runs: 159
30-day runs: 1.5K
Model's Last Updated: December 18 2024
feature-extraction

Introduction of C-RADIO

Model Details of C-RADIO

Model Overview

Description:

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

License/Terms of Use

[License] This model is governed by the NVIDIA Open Model License Agreement .

References:

AM-RADIO: Agglomerative Vision Foundation Model - Reduce All Domains Into One

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models

Model Architecture:

Architecture Type: Neural Network
Network Architecture: Vision Transformer

Input:

Input Type(s): Image
Input Format(s): Red, Green, Blue (RGB) pixel values in [0, 1] range.
Input Parameters: Two Dimensional (2D)
Other Properties Related to Input: Image resolutions up to 2048x2028 in increments of 16 pixels

Output:

Output Type(s): Embeddings
Output Format: Tensor
Output Parameters: 2D
Other Properties Related to Output: Downstream model required to leverage image features

Usage:

RADIO will return a tuple with two tensors. The summary is similar to the cls_token in ViT and is meant to represent the general concept of the entire image. It has shape (B,C) with B being the batch dimension, and C being some number of channels. The spatial_features represent more localized content which should be suitable for dense tasks such as semantic segmentation, or for integration into an LLM.

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

hf_repo = "nvidia/C-RADIO"

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)

Spatial features have shape (B,T,D) with T being the flattened spatial tokens, and D being the channels for spatial features. Note that C!=D in general. Converting to a spatial tensor format can be done using the downsampling size of the model, combined with the input tensor shape. For RADIO, the patch size is 16.

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)

The resulting tensor will have shape (B,D,H,W) , as is typically seen with computer vision models.

Software Integration:

Runtime Engine(s):

  • TAO- 24.10

Supported Hardware Microarchitecture Compatibility:

  • NVIDIA Ampere
  • NVIDIA Blackwell
  • NVIDIA Jetson
  • NVIDIA Hopper
  • NVIDIA Lovelace
  • NVIDIA Pascal
  • NVIDIA Turing
  • NVIDIA Volta

[Preferred/Supported] Operating System(s):

  • Linux
  • Linux 4 Tegra
  • QNX
  • Windows
Model Version(s):

C-RADIO.

Link: https://huggingface.co/nvidia/C-RADIO

Training, Testing, and Evaluation Datasets:

Training Dataset:

NV-CC-Img-Text-Dataset
** Data Collection Method by dataset

  • Automated
    ** Labeling Method by dataset
  • Not Applicable (no labels are needed)
    Properties: 700 Million Images
Evaluation Dataset:

Link: ImageNet
** Data Collection Method by dataset

  • Automated
    ** Labeling Method by dataset
  • 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:

Engine: PyTorch
Test Hardware: A100

Ethical Considerations (For NVIDIA Models Only):

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our 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. Users should evaluate the model for safety and quality for a specific use case and build additional guardrails as appropriate.

Please report security vulnerabilities or NVIDIA AI Concerns here .

Runs of nvidia C-RADIO on huggingface.co

2.0K
Total runs
0
24-hour runs
132
3-day runs
159
7-day runs
1.5K
30-day runs

More Information About C-RADIO huggingface.co Model

C-RADIO huggingface.co

C-RADIO huggingface.co is an AI model on huggingface.co that provides C-RADIO's model effect (), which can be used instantly with this nvidia C-RADIO model. huggingface.co supports a free trial of the C-RADIO model, and also provides paid use of the C-RADIO. Support call C-RADIO model through api, including Node.js, Python, http.

C-RADIO huggingface.co Url

https://huggingface.co/nvidia/C-RADIO

nvidia C-RADIO online free

C-RADIO huggingface.co is an online trial and call api platform, which integrates C-RADIO's modeling effects, including api services, and provides a free online trial of C-RADIO, you can try C-RADIO online for free by clicking the link below.

nvidia C-RADIO online free url in huggingface.co:

https://huggingface.co/nvidia/C-RADIO

C-RADIO install

C-RADIO is an open source model from GitHub that offers a free installation service, and any user can find C-RADIO on GitHub to install. At the same time, huggingface.co provides the effect of C-RADIO install, users can directly use C-RADIO installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

C-RADIO install url in huggingface.co:

https://huggingface.co/nvidia/C-RADIO

Url of C-RADIO

C-RADIO huggingface.co Url

Provider of C-RADIO huggingface.co

nvidia
ORGANIZATIONS

Other API from nvidia

huggingface.co

Total runs: 354.4K
Run Growth: 224.2K
Growth Rate: 61.87%
Updated: February 23 2025
huggingface.co

Total runs: 45.2K
Run Growth: -2.5K
Growth Rate: -5.68%
Updated: November 15 2023
huggingface.co

Total runs: 22.9K
Run Growth: -4.8K
Growth Rate: -21.87%
Updated: August 06 2022
huggingface.co

Total runs: 20.0K
Run Growth: 8.8K
Growth Rate: 43.88%
Updated: February 25 2025
huggingface.co

Total runs: 18.5K
Run Growth: -4.5K
Growth Rate: -23.94%
Updated: August 06 2022
huggingface.co

Total runs: 17.0K
Run Growth: -28.4K
Growth Rate: -166.92%
Updated: January 14 2025
huggingface.co

Total runs: 16.8K
Run Growth: -23.4K
Growth Rate: -118.28%
Updated: August 06 2022
huggingface.co

Total runs: 11.0K
Run Growth: 7.7K
Growth Rate: 70.40%
Updated: August 06 2022
huggingface.co

Total runs: 5.2K
Run Growth: -3.0K
Growth Rate: -58.80%
Updated: November 30 2024
huggingface.co

Total runs: 3.8K
Run Growth: 3.1K
Growth Rate: 86.67%
Updated: January 28 2025
huggingface.co

Total runs: 3.2K
Run Growth: 3.4K
Growth Rate: 92.66%
Updated: January 28 2025
huggingface.co

Total runs: 3.1K
Run Growth: -4.9K
Growth Rate: -157.37%
Updated: January 02 2025
huggingface.co

Total runs: 2.7K
Run Growth: 947
Growth Rate: 31.65%
Updated: August 06 2022
huggingface.co

Total runs: 1.7K
Run Growth: 344
Growth Rate: 20.89%
Updated: November 06 2024
huggingface.co

Total runs: 1.5K
Run Growth: -596
Growth Rate: -40.68%
Updated: December 02 2024
huggingface.co

Total runs: 877
Run Growth: 767
Growth Rate: 87.46%
Updated: January 28 2025