--- 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 | 1.16 ms | 0 - 13 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 | 1.107 ms | 0 - 11 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 | 0.382 ms | 0 - 33 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 | 0.492 ms | 0 - 21 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 | 0.277 ms | 0 - 100 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 | 0.271 ms | 0 - 50 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.501 ms | 0 - 14 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 | 0.475 ms | 0 - 12 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 | 1.16 ms | 0 - 13 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 | 1.107 ms | 0 - 11 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.279 ms | 0 - 100 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.28 ms | 0 - 52 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 | 0.669 ms | 0 - 16 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 | 0.644 ms | 0 - 14 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.dlc) | | Facial-Landmark-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.281 ms | 0 - 100 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.tflite) | | Facial-Landmark-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.276 ms | 0 - 51 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 | 0.501 ms | 0 - 14 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 | 0.475 ms | 0 - 12 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 S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.28 ms | 0 - 100 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 S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.273 ms | 0 - 50 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 S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.375 ms | 0 - 29 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx) | | Facial-Landmark-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.221 ms | 0 - 32 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 | 0.234 ms | 0 - 17 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 | 0.283 ms | 0 - 22 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx) | | Facial-Landmark-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.203 ms | 0 - 19 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 QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.197 ms | 0 - 15 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 QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.326 ms | 0 - 17 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx) | | Facial-Landmark-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.34 ms | 39 - 39 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 | 0.358 ms | 10 - 10 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection.onnx) | | Facial-Landmark-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.452 ms | 0 - 11 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 | 0.425 ms | 0 - 11 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 | 0.218 ms | 0 - 28 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 | 0.233 ms | 0 - 33 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 | 0.163 ms | 0 - 41 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 - 42 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.328 ms | 0 - 13 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 | 0.303 ms | 0 - 13 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 0.558 ms | 0 - 19 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 0.569 ms | 0 - 20 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 1.645 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 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.452 ms | 0 - 11 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 | 0.425 ms | 0 - 11 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.172 ms | 0 - 43 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.17 ms | 0 - 44 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 | 0.432 ms | 0 - 21 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 | 0.462 ms | 0 - 14 MB | NPU | [Facial-Landmark-Detection.dlc](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.dlc) | | Facial-Landmark-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.17 ms | 0 - 41 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.158 ms | 0 - 42 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 | 0.328 ms | 0 - 13 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 | 0.303 ms | 0 - 13 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 S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.175 ms | 0 - 41 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 S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.167 ms | 0 - 42 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 S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.279 ms | 0 - 29 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx) | | Facial-Landmark-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.128 ms | 0 - 29 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 - 30 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 | 0.197 ms | 0 - 31 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx) | | Facial-Landmark-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.148 ms | 0 - 15 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 QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.128 ms | 0 - 17 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 QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.224 ms | 0 - 18 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx) | | Facial-Landmark-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.213 ms | 32 - 32 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 | 0.306 ms | 4 - 4 MB | NPU | [Facial-Landmark-Detection.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.onnx) | ## Installation Install the package via pip: ```bash pip install "qai-hub-models[facemap-3dmm]" ``` ## 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.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 ``` ``` Profiling Results ------------------------------------------------------------ Facial-Landmark-Detection Device : cs_8275 (ANDROID 14) Runtime : TFLITE Estimated inference time (ms) : 1.2 Estimated peak memory usage (MB): [0, 13] Total # Ops : 37 Compute Unit(s) : npu (37 ops) gpu (0 ops) cpu (0 ops) ``` ## 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 S24") # 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. [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). * 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) ## 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).