Update README.md

README.md

@@ -1,199 +1,153 @@
 ---
-library_name: transformers
-tags: []
+license: other
+license_name: nvclv1
+license_link: LICENSE
+datasets:
+- ILSVRC/imagenet-21k
+pipeline_tag: image-feature-extraction
 ---
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+[**MambaVision: A Hybrid Mamba-Transformer Vision Backbone**](https://arxiv.org/abs/2407.08083).
 
+## Model Overview
 
+We have developed the first hybrid model for computer vision which leverages the strengths of Mamba and Transformers. Specifically, our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. In addition, we conducted a comprehensive ablation study on the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results demonstrate that equipping the Mamba architecture with several self-attention blocks at the final layers greatly improves the modeling capacity to capture long-range spatial dependencies. Based on our findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria.
 
-## Model Details
+## Model Performance
 
-### Model Description
+MambaVision-L3-256-21K is pretrained on ImageNet-21K dataset and finetuned on ImageNet-1K. Both pretraining and finetuning are performed at 256 x 256 resolution.
 
-<!-- Provide a longer summary of what this model is. -->
+<table>
+  <tr>
+    <th>Name</th>
+    <th>Acc@1(%)</th>
+    <th>Acc@5(%)</th>
+    <th>#Params(M)</th>
+    <th>FLOPs(G)</th>
+    <th>Resolution</th>
+  </tr>
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+<tr>
+    <td>MambaVision-L3-256-21K</td>
+    <td>87.3</td>
+    <td>98.3</td>
+    <td>739.6</td>
+    <td>122.3</td>
+    <td>256x256</td>
+</tr>
 
-- **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]
+</table>
 
-<!-- Provide the basic links for the model. -->
+In addition, the MambaVision models demonstrate a strong performance by achieving a new SOTA Pareto-front in
+terms of Top-1 accuracy and throughput. 
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+<p align="center">
+<img src="https://github.com/NVlabs/MambaVision/assets/26806394/79dcf841-3966-4b77-883d-76cd5e1d4320" width=70% height=70% 
+class="center">
+</p>
 
-## 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. -->
+## Model Usage
 
-### Direct Use
+It is highly recommended to install the requirements for MambaVision by running the following:
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
+```Bash
+pip install mambavision
+```
 
-### Downstream Use [optional]
+For each model, we offer two variants for image classification and feature extraction that can be imported with 1 line of code. 
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Image Classification
 
-[More Information Needed]
+In the following example, we demonstrate how MambaVision can be used for image classification. 
 
-### Out-of-Scope Use
+Given the following image from [COCO dataset](https://cocodataset.org/#home)  val set as an input:
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+<p align="center">
+<img src="https://cdn-uploads.huggingface.co/production/uploads/64414b62603214724ebd2636/4duSnqLf4lrNiAHczSmAN.jpeg" width=70% height=70% 
+class="center">
+</p>
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+The following snippet can be used for image classification:
 
-[More Information Needed]
+```Python
+from transformers import AutoModelForImageClassification
+from PIL import Image
+from timm.data.transforms_factory import create_transform
+import requests
 
-### Recommendations
+model = AutoModelForImageClassification.from_pretrained("nvidia/MambaVision-L3-256-21K", trust_remote_code=True)
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+# eval mode for inference
+model.cuda().eval()
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+# prepare image for the model
+url = 'http://images.cocodataset.org/val2017/000000020247.jpg'
+image = Image.open(requests.get(url, stream=True).raw)
+input_resolution = (3, 256, 256)  # MambaVision supports any input resolutions
 
-## How to Get Started with the Model
+transform = create_transform(input_size=input_resolution,
+                             is_training=False,
+                             mean=model.config.mean,
+                             std=model.config.std,
+                             crop_mode=model.config.crop_mode,
+                             crop_pct=model.config.crop_pct)
 
-Use the code below to get started with the model.
+inputs = transform(image).unsqueeze(0).cuda()
+# model inference
+outputs = model(inputs)
+logits = outputs['logits'] 
+predicted_class_idx = logits.argmax(-1).item()
+print("Predicted class:", model.config.id2label[predicted_class_idx])
+```
 
-[More Information Needed]
+The predicted label is ```brown bear, bruin, Ursus arctos.```
 
-## Training Details
+### Feature Extraction
 
-### Training Data
+MambaVision can also be used as a generic feature extractor. 
 
-<!-- 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. -->
+Specifically, we can extract the outputs of each stage of model (4 stages) as well as the final averaged-pool features that are flattened. 
 
-[More Information Needed]
+The following snippet can be used for feature extraction:
 
-### Training Procedure
+```Python
+from transformers import AutoModel
+from PIL import Image
+from timm.data.transforms_factory import create_transform
+import requests
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+model = AutoModel.from_pretrained("nvidia/MambaVision-L3-256-21K", trust_remote_code=True)
 
-#### Preprocessing [optional]
+# eval mode for inference
+model.cuda().eval()
 
-[More Information Needed]
+# prepare image for the model
+url = 'http://images.cocodataset.org/val2017/000000020247.jpg'
+image = Image.open(requests.get(url, stream=True).raw)
+input_resolution = (3, 256, 256)  # MambaVision supports any input resolutions
 
+transform = create_transform(input_size=input_resolution,
+                             is_training=False,
+                             mean=model.config.mean,
+                             std=model.config.std,
+                             crop_mode=model.config.crop_mode,
+                             crop_pct=model.config.crop_pct)
+inputs = transform(image).unsqueeze(0).cuda()
+# model inference
+out_avg_pool, features = model(inputs)
+print("Size of the averaged pool features:", out_avg_pool.size())  # torch.Size([1, 1568])
+print("Number of stages in extracted features:", len(features)) # 4 stages
+print("Size of extracted features in stage 1:", features[0].size()) # torch.Size([1, 196, 128, 128])
+print("Size of extracted features in stage 4:", features[3].size()) # torch.Size([1, 1568, 16, 16])
+```
 
-#### 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 -->
+### License: 
 
-#### 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]
+[NVIDIA Source Code License-NC](https://huggingface.co/nvidia/MambaVision-L3-256-21K/blob/main/LICENSE)