--- 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 | 1.161 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 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 1.144 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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.385 ms | 0 - 39 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 | 0.555 ms | 0 - 25 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 | 0.286 ms | 0 - 101 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 | 0.297 ms | 0 - 49 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 | 0.487 ms | 0 - 34 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 | 0.511 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 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.5 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 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 1.161 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 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 1.144 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 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.307 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 | 0.301 ms | 0 - 41 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 | 0.665 ms | 0 - 23 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 | 0.652 ms | 0 - 22 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 | 0.29 ms | 0 - 99 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 | 0.297 ms | 0 - 49 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 | 0.511 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 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.5 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 | TFLITE | 0.21 ms | 0 - 38 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 | 0.224 ms | 0 - 24 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 | 0.335 ms | 0 - 26 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 | 0.193 ms | 0 - 21 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 | 0.195 ms | 0 - 24 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 | 0.308 ms | 0 - 16 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 Gen5 Mobile | TFLITE | 0.189 ms | 0 - 24 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 Gen5 Mobile | QNN_DLC | 0.196 ms | 0 - 19 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 Gen5 Mobile | ONNX | 0.315 ms | 0 - 21 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 | 0.359 ms | 35 - 35 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 | 0.392 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 RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 0.577 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 | 0.54 ms | 0 - 98 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 | 3.02 ms | 3 - 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 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.465 ms | 0 - 17 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 | 0.434 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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.23 ms | 0 - 37 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 | 0.248 ms | 0 - 38 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 | 0.179 ms | 0 - 42 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 | 0.169 ms | 0 - 41 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 | 0.374 ms | 0 - 43 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 | 0.332 ms | 0 - 17 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 | 0.312 ms | 0 - 18 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 | 2.049 ms | 0 - 2 MB | NPU | [Facial-Landmark-Detection.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection/blob/main/Facial-Landmark-Detection_w8a8.tflite) | | Facial-Landmark-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 1.518 ms | 0 - 16 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 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.465 ms | 0 - 17 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 | 0.434 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 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.182 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 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.169 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 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.471 ms | 0 - 23 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 | 0.442 ms | 0 - 23 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 | 0.173 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 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.163 ms | 0 - 43 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 | 0.332 ms | 0 - 17 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 | 0.312 ms | 0 - 18 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 | 0.145 ms | 0 - 32 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 | 0.126 ms | 0 - 35 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 | 0.223 ms | 0 - 38 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 | 0.122 ms | 0 - 27 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 | 0.11 ms | 0 - 25 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 | 0.211 ms | 0 - 24 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 - 27 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 | 0.221 ms | 0 - 26 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 | 1.563 ms | 2 - 20 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 Gen5 Mobile | TFLITE | 0.119 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 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.123 ms | 0 - 19 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 Gen5 Mobile | ONNX | 0.213 ms | 0 - 20 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 | 0.239 ms | 31 - 31 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 | 0.236 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). * 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).