Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,172 @@
+---
+library_name: pytorch
+license: bsd-3-clause
+pipeline_tag: keypoint-detection
+tags:
+- quantized
+- android
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/facemap_3dmm_quantized/web-assets/model_demo.png)
+
+# Facial-Landmark-Detection-Quantized: Optimized for Mobile Deployment
+## Facial landmark predictor with 3DMM
+
+
+Real-time 3D facial landmark detection optimized for mobile and edge.
+
+This model is an implementation of Facial-Landmark-Detection-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
+
+
+This repository provides scripts to run Facial-Landmark-Detection-Quantized on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/facemap_3dmm_quantized).
+
+
+### Model Details
+
+- **Model Type:** Pose estimation
+- **Model Stats:**
+  - Input resolution: 128x128
+  - Number of parameters: 5.424M
+  - Model size: 5.314MB
+
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.237 ms | 0 - 5 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
+| Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.191 ms | 0 - 9 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
+| Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.182 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.81 ms | 0 - 7 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.228 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 1.727 ms | 0 - 5 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.23 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 0.661 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.228 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 0.677 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.283 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
+| Facial-Landmark-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.335 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
+
+
+
+
+## Installation
+
+This model can be installed as a Python package via pip.
+
+```bash
+pip install "qai-hub-models[facemap_3dmm_quantized]"
+```
+
+
+
+## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
+
+Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
+Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
+
+With this API token, you can configure your client to run models on the cloud
+hosted devices.
+```bash
+qai-hub configure --api_token API_TOKEN
+```
+Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
+
+
+
+## Demo off target
+
+The package contains a simple end-to-end demo that downloads pre-trained
+weights and runs this model on a sample input.
+
+```bash
+python -m qai_hub_models.models.facemap_3dmm_quantized.demo
+```
+
+The above demo runs a reference implementation of pre-processing, model
+inference, and post processing.
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.facemap_3dmm_quantized.demo
+```
+
+
+### Run model on a cloud-hosted device
+
+In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
+device. This script does the following:
+* Performance check on-device on a cloud-hosted device
+* Downloads compiled assets that can be deployed on-device for Android.
+* Accuracy check between PyTorch and on-device outputs.
+
+```bash
+python -m qai_hub_models.models.facemap_3dmm_quantized.export
+```
+```
+Profiling Results
+------------------------------------------------------------
+Facial-Landmark-Detection-Quantized
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : QNN                    
+Estimated inference time (ms)   : 0.2                    
+Estimated peak memory usage (MB): [0, 5]                 
+Total # Ops                     : 55                     
+Compute Unit(s)                 : NPU (55 ops)           
+```
+
+
+
+
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.facemap_3dmm_quantized.demo --on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.facemap_3dmm_quantized.demo -- --on-device
+```
+
+
+## Deploying compiled model to Android
+
+
+The models can be deployed using multiple runtimes:
+- TensorFlow Lite (`.tflite` export): [This
+  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
+  guide to deploy the .tflite model in an Android application.
+
+
+- QNN (`.so` export ): This [sample
+  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
+provides instructions on how to use the `.so` shared library  in an Android application.
+
+
+## View on Qualcomm® AI Hub
+Get more details on Facial-Landmark-Detection-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/facemap_3dmm_quantized).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of Facial-Landmark-Detection-Quantized can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+
+
+
+## References
+* [None](None)
+* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)
+
+
+
+## Community
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
+
+