nvidia
/

C-RADIOv4-SO400M

@@ -1,199 +1,277 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: other
+license_name: nvidia-open-model-license
+license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
 library_name: transformers
 ---
+# 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.
+C-RADIOv4 models are available in multiple sizes:
+* Shape-Optimized (431M parameters).
+* Huge (653M parameters).
+C-RADIOv4 was trained using an updated set of teach models:
+* [SigLIP2-g](https://huggingface.co/google/siglip2-giant-opt-patch16-384)
+* [DINOv3-7B](https://huggingface.co/facebook/dinov3-vit7b16-pretrain-lvd1689m)
+* [SAM3](https://huggingface.co/facebook/sam3)
+This model is ready for commercial/non-commercial use.
+### License/Terms of Use
+GOVERNING TERMS: 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).
+## Deployment Geography
+Global
+## Use Case
+The embeddings generated by this model are expected to be used by a downstream application.
+For example:
+* Image-level understanding (image classification, curation, etc.).
+* Dense processing (semantic segmentation, depth estimation, etc.).
+* Integration into a Vision-Language Model.
+## Release Date
+Hugging Face: 01/23/2026 via [RADIO Collection of Models](https://huggingface.co/collections/nvidia/radio-669f77f1dd6b153f007dd1c6).
+## References
+* [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://arxiv.org/abs/2312.06709)
+* [PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation](https://arxiv.org/abs/2410.01680)
+* [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://arxiv.org/abs/2412.07679)
+* [FeatSharp: Your Vision Model Features, Sharper](https://arxiv.org/abs/2502.16025)
+* [C-RADIOv4 (Tech Report)](https://arxiv.org/abs/2601.17237)
+## Model Architecture
+**Architecture Type:** Neural Network  <br>
+**Network Architecture:** Vision Transformer <br>
+**Number of model parameters:** -B size: 98M, -L size: 320M, -SO400M size: 431M, -H size: 653M <br>
+## Input
+**Input Type(s):** Image <br>
+**Input Format(s):** Red, Green, Blue (RGB) <br>
+**Input Parameters:** Two Dimensional (2D) <br>
+**Other Properties Related to Input:** Image resolutions up to 2048x2028 in increments of 16 pixels <br>
+## Output
+**Output Type(s):** Embeddings <br>
+**Output Format:** Tensor <br>
+**Output Parameters:** Two Dimensional 2D <br>
+**Other Properties Related to Output:** Downstream model required to leverage image features. Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
+## 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.
+```python
+import torch
+from PIL import Image
+from transformers import AutoModel, CLIPImageProcessor
+hf_repo = "nvidia/C-RADIOv4-SO400M"
+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.
+```Python
+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-6.1] <br>
+**Supported Hardware Microarchitecture Compatibility:** <br>
+* NVIDIA Ampere <br>
+* NVIDIA Blackwell <br>
+* NVIDIA Jetson  <br>
+* NVIDIA Hopper <br>
+* NVIDIA Lovelace <br>
+* NVIDIA Pascal <br>
+* NVIDIA Turing <br>
+* NVIDIA Volta <br>
+**[Preferred/Supported] Operating System(s):** <br>
+* Linux
+* Linux 4 Tegra
+* QNX
+* Windows
+The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
+This AI model can be embedded as an Application Programming Interface (API) call into the software environment described above.
+## Model Version(s)
+* C-RADIOv4-SO400M (400M parameters).
+* C-RADIOv4-H (653M parameters).
+**Links:**
+* https://huggingface.co/nvidia/C-RADIOv4-B
+* https://huggingface.co/nvidia/C-RADIOv4-L
+* https://huggingface.co/nvidia/C-RADIOv4-SO400M
+* https://huggingface.co/nvidia/C-RADIOv4-H
+# Training and Evaluation Datasets
+## Training Dataset
+** Data Modality
+NV-CC-Img-Text-Dataset  <br>
+** Data Modality <br>
+* Image <br>
+** Image Training Data Size <br>
+* 1 Million to 1 Billion Images <br>
+** Data Collection Method by dataset <br>
+* Automated <br>
+** Labeling Method by dataset <br>
+* Not Applicable (no labels are needed) <br>
+**Properties:** 700 Million Images <br>
+## Evaluation Datasets
+ImageNet <br>
+** Link <br>
+* [ImageNet](https://www.image-net.org/) <br>
+** Data Collection <br>
+* Automated  <br>
+** Labeling Method <br>
+* Human  <br>
+** Training Images <br>
+* 1,281,167 <br>
+** Validation Images <br>
+* 50,000 <br>
+** Test Images <br>
+* 100,000
+To perform the semantic segmentation evaluation, we use training sets from ADE20K and PascalVOC to train a linear layer, and subsequently performed evaluations on the validation set.
+See below for further details:
+ADE20k <br>
+** Link <br>
+* [ADE20K](https://ade20k.csail.mit.edu/) <br>
+** Data Collection <br>
+* Human  <br>
+** Labeling Method <br>
+* Human  <br>
+** Training Images <br>
+* 25,574 <br>
+** Validation Images <br>
+* 2,000 <br>
+Pascal VOC <br>
+** Link <br>
+* [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) <br>
+** Data Collection <br>
+* Human  <br>
+** Labeling Method <br>
+* Human  <br>
+** Training Images <br>
+* 1,464 <br>
+** Validation Images <br>
+* 1,449 <br>
+| Benchmark | C-RADIOv3-B | C-RADIOv4-B |  C-RADIOv3-L |  C-RADIOv4-L | C-RADIOv4-SO400M | C-RADIOv3-H | C-RADIOv4-H |
+|-----------|-------------|-------------|-------------|---------------|------------------|-------------|-------------|
+| **ImageNet Classification (Top1 accuracy)** | | | | |
+| Zero-Shot | 71.30       | 66.45       | 79.95       | 79.67         | 82.01            | 82.65       | 82.91       |
+| KNN       | 81.22       | 80.12       | 84.33       | 85.16         | 85.75            | 86.23       | 86.27       |
+| **ADE20k Semantic Segmentation (mIoU)**     | 49.79 | 50.48 | 51.87 | 54.64 | 55.14 | 52.75 | 55.05 |
+| **Pascal VOC Semantic Segmentation (mIoU)** | 84.68 | 85.47 | 86.12 | 86.55 | 87.22 | 86.41 | 87.64 |
+## Inference
+**Acceleration Engine:** Tensor(RT), Tensor(RT)-LLM <br>
+**Engine:** PyTorch <br>
+**Test Hardware:** H100 <br>
+## Ethical Considerations
+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.
+Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included.
+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 model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+### Bias
+Field                                                                                               |  Response
+:---------------------------------------------------------------------------------------------------|:---------------
+Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing:  |  None
+Measures taken to mitigate against unwanted bias:                                                   |  None
+### Explainability
+Field                                                                                                  |  Response
+:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
+Intended Task/Domain:                                                                                  |  Visual Feature Extraction
+Model Type:                                                                                            |  Vision Transformer
+Intended Users:                                                                                        |  Developers of downstream vision applications
+Output:                                                                                                |  Image embeddings
+Describe how the model works:                                                                          |  The model takes an image as input, processes the image through multiple transformer blocks, and outputs summary and patch embeddings.
+Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:  |  Not Applicable
+Technical Limitations:                                                                                 |  This model generates image embeddings that can be used by a downstream model to, for example, classify images. The downstream model must be trained to leverage the visual embeddings. This model is only tested on input resolutions ranging from 256 to 2048, in increments of 16 pixels. This model may fail to surface information about the orientation of objects (e.g. whether a traffic sign points left/right).
+Verified to have met prescribed NVIDIA quality standards:  |  Yes
+Performance Metrics:                                                                                   |  Image classification accuracy, semantic segmentation mean-over-intersection.
+Potential Known Risks:                                                                                 |  This model may not perform well on visual domains that are not represented in the training data. The generated embeddings might fail to disambiguate differences that appear evident to humans (e.g. two images showing different breeds of dogs might in fact produce very similar embeddings). Domain-specific evaluation is required for the target application.
+Licensing:                                                                                             |  [NVIDIA Open Model License](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf)
+### Privacy
+Field                                                                                                                              |  Response
+:----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------
+Generatable or reverse engineerable personal data?                                                                               |  No
+Personal data used to create this model?                                                                                       |  None Known
+How often is dataset reviewed?                                                                                                     |  Before Every Release
+Is there provenance for all datasets used in training?                                                                                |  Yes
+Does data labeling (annotation, metadata) comply with privacy laws?                                                                |  Yes
+Is data compliant with data subject requests for data correction or removal, if such a request was made?                           |  Yes
+Was data from user interactions with the AI model (e.g. user input and prompts) used to train the model?                           | No
+Applicable Privacy Policy                                                                          | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/
+### Safety
+Field                                               |  Response
+:---------------------------------------------------|:----------------------------------
+Model Application Field(s):                               |  Generation of visual embeddings
+Describe the life critical impact (if present).   |  Not Applicable
+Use Case Restrictions:                              |  Abide by NVIDIA Open Model License Agreement
+Model and dataset restrictions:            |  The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.