MediaPipe-Face-Detection: 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 found here.
This repository provides scripts to run MediaPipe-Face-Detection on Qualcomm® devices. More details on model performance across various devices, can be found here.
Model Details
- Model Type: Model_use_case.object_detection
- Model Stats:
- Input resolution: 256x256
- Number of output classes: 6
- Number of parameters (FaceDetector): 135K
- Model size (FaceDetector) (w8a8): 260 KB
- Number of parameters (FaceLandmarkDetector): 603K
- Model size (FaceLandmarkDetector) (w8a8): 750 KB
- Model size (FaceDetector) (float): 557 KB
- Model size (FaceLandmarkDetector) (float): 2.33 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| FaceDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.001 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 2.904 ms | 1 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.777 ms | 0 - 29 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.75 ms | 1 - 29 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.568 ms | 0 - 6 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.54 ms | 1 - 6 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.951 ms | 1 - 9 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.089 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.059 ms | 1 - 22 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3.001 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 2.904 ms | 1 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.564 ms | 0 - 7 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.541 ms | 1 - 6 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1.144 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 1.107 ms | 1 - 26 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.566 ms | 0 - 5 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.54 ms | 1 - 6 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.089 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.059 ms | 1 - 22 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.406 ms | 0 - 32 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.398 ms | 1 - 29 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.632 ms | 0 - 26 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.348 ms | 0 - 27 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.331 ms | 1 - 26 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.53 ms | 0 - 28 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.282 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.275 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.488 ms | 1 - 24 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.695 ms | 7 - 7 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.86 ms | 2 - 2 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.843 ms | 0 - 19 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 0.859 ms | 0 - 17 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.299 ms | 0 - 35 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.357 ms | 0 - 28 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.199 ms | 0 - 10 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.222 ms | 0 - 10 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.445 ms | 0 - 9 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.447 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.446 ms | 0 - 17 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.843 ms | 0 - 19 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 0.859 ms | 0 - 17 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.203 ms | 0 - 10 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.227 ms | 0 - 10 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.563 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 0.584 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.207 ms | 0 - 10 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.222 ms | 0 - 4 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 0.447 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.446 ms | 0 - 17 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.151 ms | 0 - 30 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.159 ms | 0 - 29 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.318 ms | 0 - 30 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.125 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.135 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.274 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.106 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.127 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.26 ms | 0 - 19 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.315 ms | 8 - 8 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.374 ms | 0 - 0 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.678 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 0.66 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.295 ms | 0 - 33 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.313 ms | 0 - 36 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.244 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.245 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.478 ms | 0 - 11 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.463 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.439 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 0.637 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 0.67 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 6.499 ms | 6 - 18 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 5.054 ms | 0 - 3 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 5.44 ms | 6 - 9 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.678 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 0.66 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.243 ms | 0 - 11 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.248 ms | 0 - 11 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.585 ms | 0 - 27 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 0.577 ms | 0 - 27 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.248 ms | 0 - 11 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.244 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 0.463 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.439 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.17 ms | 0 - 34 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.164 ms | 0 - 35 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.309 ms | 0 - 31 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.139 ms | 0 - 27 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.139 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.266 ms | 0 - 26 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 0.256 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 0.244 ms | 0 - 29 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 6.745 ms | 7 - 24 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.133 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.13 ms | 0 - 30 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.279 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceDetector | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.352 ms | 0 - 0 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceDetector | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.378 ms | 0 - 0 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 0.499 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 0.484 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.219 ms | 0 - 32 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.211 ms | 0 - 26 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.156 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.154 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 0.391 ms | 0 - 13 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.339 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 0.329 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 0.398 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 0.414 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 3.222 ms | 0 - 12 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 2.752 ms | 0 - 2 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 2.485 ms | 2 - 6 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 0.499 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 0.484 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 0.164 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.157 ms | 0 - 5 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 0.453 ms | 0 - 23 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 0.457 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 0.164 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.156 ms | 0 - 12 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 0.339 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.329 ms | 0 - 18 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.115 ms | 0 - 24 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.115 ms | 0 - 30 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.263 ms | 0 - 30 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.1 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.094 ms | 0 - 25 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.233 ms | 0 - 19 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 0.154 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 0.149 ms | 0 - 22 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 3.028 ms | 0 - 15 MB | CPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.1 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.tflite |
| FaceLandmarkDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.094 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.233 ms | 0 - 21 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
| FaceLandmarkDetector | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.257 ms | 3 - 3 MB | NPU | MediaPipe-Face-Detection.dlc |
| FaceLandmarkDetector | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.294 ms | 0 - 0 MB | NPU | MediaPipe-Face-Detection.onnx.zip |
Installation
Install the package via pip:
pip install qai-hub-models
Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
Sign-in to Qualcomm® AI Hub Workbench 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.
qai-hub configure --api_token API_TOKEN
Navigate to 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.
python -m qai_hub_models.models.mediapipe_face.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.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.
python -m qai_hub_models.models.mediapipe_face.export
How does this work?
This export script leverages Qualcomm® AI Hub 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.
import torch
import qai_hub as hub
from qai_hub_models.models.mediapipe_face 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.
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.
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.
Deploying compiled model to Android
The models can be deployed using multiple runtimes:
TensorFlow Lite (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.soexport ): This sample app provides instructions on how to use the.soshared library in an Android application.
View on Qualcomm® AI Hub
Get more details on MediaPipe-Face-Detection's performance across various devices here. Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of MediaPipe-Face-Detection can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
- Downloads last month
- 2,232
