--- library_name: pytorch license: other tags: - backbone - android pipeline_tag: keypoint-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/facemap_3dmm/web-assets/model_demo.png) # Facial-Landmark-Detection: Optimized for Mobile Deployment ## Real-time 3D facial landmark detection optimized for mobile and edge Detects facial landmarks (eg, nose, mouth, etc.). This model's architecture was developed by Qualcomm. The model was trained by Qualcomm on a proprietary dataset of faces, but can be used on any image. This repository provides scripts to run Facial-Landmark-Detection on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/facemap_3dmm). ### Model Details - **Model Type:** Model_use_case.pose_estimation - **Model Stats:** - Input resolution: 128x128 - Number of parameters: 5.42M - Model size (float): 20.7 MB - Model size (w8a8): 5.27 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | Facial-Landmark-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1.131 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 1.137 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.481 ms | 0 - 146 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.551 ms | 0 - 130 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.281 ms | 0 - 10 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.298 ms | 0 - 3 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.514 ms | 0 - 15 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx.zip) | | Facial-Landmark-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.503 ms | 0 - 116 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.515 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 1.131 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 1.137 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.641 ms | 0 - 121 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 0.64 ms | 0 - 120 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 0.503 ms | 0 - 116 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.515 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.225 ms | 0 - 144 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.236 ms | 0 - 129 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.332 ms | 0 - 103 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx.zip) | | Facial-Landmark-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.19 ms | 0 - 120 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.198 ms | 0 - 118 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.318 ms | 0 - 90 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx.zip) | | Facial-Landmark-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 0.189 ms | 0 - 119 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 0.196 ms | 0 - 118 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 0.316 ms | 0 - 91 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx.zip) | | Facial-Landmark-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.367 ms | 0 - 0 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.394 ms | 10 - 10 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® QCM6690 | TFLITE | 0.604 ms | 0 - 123 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® QCM6690 | QNN_DLC | 0.597 ms | 0 - 124 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® QCM6690 | ONNX | 1.664 ms | 0 - 13 MB | CPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 0.604 ms | 0 - 7 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | QNN_DLC | 0.693 ms | 0 - 2 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 2.776 ms | 2 - 12 MB | CPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.46 ms | 0 - 114 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 0.43 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.27 ms | 0 - 138 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.247 ms | 0 - 137 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.169 ms | 0 - 3 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.17 ms | 0 - 2 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.365 ms | 0 - 9 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.331 ms | 0 - 114 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.311 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.46 ms | 0 - 114 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 0.43 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.441 ms | 0 - 120 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 0.443 ms | 0 - 121 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 0.331 ms | 0 - 114 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.311 ms | 0 - 115 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.14 ms | 0 - 139 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.14 ms | 0 - 139 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.227 ms | 0 - 114 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.123 ms | 0 - 118 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.118 ms | 0 - 119 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.209 ms | 0 - 91 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 0.224 ms | 0 - 123 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 0.22 ms | 0 - 124 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 1.553 ms | 2 - 18 MB | CPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 0.126 ms | 0 - 116 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 0.119 ms | 0 - 117 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 0.27 ms | 0 - 93 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | | Facial-Landmark-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.236 ms | 0 - 0 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.232 ms | 5 - 5 MB | NPU | [Facial-Landmark-Detection.onnx.zip](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx.zip) | ## Installation Install the package via pip: ```bash # NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported. pip install "qai-hub-models[facemap-3dmm]" ``` ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.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://workbench.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.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.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.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/facemap_3dmm/qai_hub_models/models/Facial-Landmark-Detection/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model on-device. Lets go through each step below in detail: Step 1: **Compile model for on-device deployment** To compile a PyTorch model for on-device deployment, we first trace the model in memory using the `jit.trace` and then call the `submit_compile_job` API. ```python import torch import qai_hub as hub from qai_hub_models.models.facemap_3dmm import Model # Load the model torch_model = Model.from_pretrained() # Device device = hub.Device("Samsung Galaxy S25") # Trace model input_shape = torch_model.get_input_spec() sample_inputs = torch_model.sample_inputs() pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()]) # Compile model on a specific device compile_job = hub.submit_compile_job( model=pt_model, device=device, input_specs=torch_model.get_input_spec(), ) # Get target model to run on-device target_model = compile_job.get_target_model() ``` Step 2: **Performance profiling on cloud-hosted device** After compiling models from step 1. Models can be profiled model on-device using the `target_model`. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics. ```python profile_job = hub.submit_profile_job( model=target_model, device=device, ) ``` Step 3: **Verify on-device accuracy** To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device. ```python input_data = torch_model.sample_inputs() inference_job = hub.submit_inference_job( model=target_model, device=device, inputs=input_data, ) on_device_output = inference_job.download_output_data() ``` With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output. **Note**: This on-device profiling and inference requires access to Qualcomm® AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup). ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash python -m qai_hub_models.models.facemap_3dmm.demo --eval-mode 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.demo -- --eval-mode 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's performance across various devices [here](https://aihub.qualcomm.com/models/facemap_3dmm). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of Facial-Landmark-Detection can be found [here](https://github.com/quic/ai-hub-models/blob/main/LICENSE). ## 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).