|
--- |
|
library_name: pytorch |
|
license: apache-2.0 |
|
tags: |
|
- real_time |
|
- quantized |
|
- android |
|
pipeline_tag: object-detection |
|
|
|
--- |
|
|
|
 |
|
|
|
# MediaPipe-Face-Detection-Quantized: Optimized for Mobile Deployment |
|
## Detect faces and locate facial features in real-time video and image streams |
|
|
|
|
|
Designed for sub-millisecond processing, this model predicts bounding boxes and pose skeletons (left eye, right eye, nose tip, mouth, left eye tragion, and right eye tragion) of faces in an image. |
|
|
|
This model is an implementation of MediaPipe-Face-Detection-Quantized found [here](https://github.com/zmurez/MediaPipePyTorch/). |
|
|
|
|
|
This repository provides scripts to run MediaPipe-Face-Detection-Quantized on Qualcomm® devices. |
|
More details on model performance across various devices, can be found |
|
[here](https://aihub.qualcomm.com/models/mediapipe_face_quantized). |
|
|
|
|
|
### Model Details |
|
|
|
- **Model Type:** Object detection |
|
- **Model Stats:** |
|
- Input resolution: 256x256 |
|
- Number of output classes: 6 |
|
- Number of parameters (MediaPipeFaceDetector): 135K |
|
- Model size (MediaPipeFaceDetector): 255 KB |
|
- Number of parameters (MediaPipeFaceLandmarkDetector): 603K |
|
- Model size (MediaPipeFaceLandmarkDetector): 746 KB |
|
|
|
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
|
|---|---|---|---|---|---|---|---|---| |
|
| MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.264 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.242 ms | 0 - 3 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.so) | |
|
| MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.746 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.onnx) | |
|
| MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.181 ms | 0 - 27 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.165 ms | 0 - 21 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.so) | |
|
| MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.519 ms | 0 - 34 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.onnx) | |
|
| MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.156 ms | 0 - 23 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.167 ms | 0 - 23 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.514 ms | 0 - 23 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.onnx) | |
|
| MediaPipeFaceDetector | SA7255P ADP | SA7255P | TFLITE | 2.032 ms | 0 - 17 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | SA7255P ADP | SA7255P | QNN | 1.872 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.267 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.243 ms | 0 - 2 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | SA8295P ADP | SA8295P | TFLITE | 0.618 ms | 0 - 22 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | SA8295P ADP | SA8295P | QNN | 0.57 ms | 0 - 18 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.265 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.245 ms | 0 - 2 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | SA8775P ADP | SA8775P | TFLITE | 0.552 ms | 0 - 17 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | SA8775P ADP | SA8775P | QNN | 0.501 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.709 ms | 0 - 25 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.63 ms | 0 - 14 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 5.046 ms | 0 - 2 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 2.032 ms | 0 - 17 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 1.872 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.271 ms | 0 - 6 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.245 ms | 0 - 3 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.552 ms | 0 - 17 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.501 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.38 ms | 0 - 31 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.tflite) | |
|
| MediaPipeFaceDetector | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.357 ms | 0 - 24 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.333 ms | 0 - 0 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.772 ms | 1 - 1 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceDetector.onnx) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.182 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.154 ms | 0 - 2 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.so) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.505 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.onnx) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.131 ms | 0 - 24 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.116 ms | 0 - 21 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.so) | |
|
| MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.329 ms | 28 - 52 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.onnx) | |
|
| MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.141 ms | 0 - 19 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.123 ms | 0 - 20 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.29 ms | 0 - 21 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.onnx) | |
|
| MediaPipeFaceLandmarkDetector | SA7255P ADP | SA7255P | TFLITE | 0.88 ms | 0 - 12 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | SA7255P ADP | SA7255P | QNN | 0.796 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.184 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.153 ms | 0 - 2 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | SA8295P ADP | SA8295P | TFLITE | 0.499 ms | 0 - 20 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | SA8295P ADP | SA8295P | QNN | 0.462 ms | 0 - 17 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.181 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.151 ms | 0 - 2 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | SA8775P ADP | SA8775P | TFLITE | 0.424 ms | 0 - 12 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | SA8775P ADP | SA8775P | QNN | 0.374 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.42 ms | 0 - 15 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.388 ms | 0 - 13 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 2.782 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 0.88 ms | 0 - 12 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 0.796 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.171 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.149 ms | 0 - 3 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.424 ms | 0 - 12 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.374 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.281 ms | 0 - 22 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.tflite) | |
|
| MediaPipeFaceLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.266 ms | 0 - 23 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.225 ms | 0 - 0 MB | FP16 | NPU | Use Export Script | |
|
| MediaPipeFaceLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.474 ms | 0 - 0 MB | FP16 | NPU | [MediaPipe-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection-Quantized/blob/main/MediaPipeFaceLandmarkDetector.onnx) | |
|
|
|
|
|
|
|
|
|
## Installation |
|
|
|
|
|
Install the package via pip: |
|
```bash |
|
pip install "qai-hub-models[mediapipe-face-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.mediapipe_face_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.mediapipe_face_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.mediapipe_face_quantized.export |
|
``` |
|
``` |
|
Profiling Results |
|
------------------------------------------------------------ |
|
MediaPipeFaceDetector |
|
Device : Samsung Galaxy S23 (13) |
|
Runtime : TFLITE |
|
Estimated inference time (ms) : 0.3 |
|
Estimated peak memory usage (MB): [0, 11] |
|
Total # Ops : 121 |
|
Compute Unit(s) : NPU (121 ops) |
|
|
|
------------------------------------------------------------ |
|
MediaPipeFaceLandmarkDetector |
|
Device : Samsung Galaxy S23 (13) |
|
Runtime : TFLITE |
|
Estimated inference time (ms) : 0.2 |
|
Estimated peak memory usage (MB): [0, 11] |
|
Total # Ops : 116 |
|
Compute Unit(s) : NPU (116 ops) |
|
``` |
|
|
|
|
|
|
|
|
|
|
|
## 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 MediaPipe-Face-Detection-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/mediapipe_face_quantized). |
|
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) |
|
|
|
|
|
## License |
|
* The license for the original implementation of MediaPipe-Face-Detection-Quantized can be found |
|
[here](https://github.com/zmurez/MediaPipePyTorch/blob/master/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 |
|
* [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://arxiv.org/abs/1907.05047) |
|
* [Source Model Implementation](https://github.com/zmurez/MediaPipePyTorch/) |
|
|
|
|
|
|
|
## 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:[email protected]). |
|
|
|
|
|
|
