Hugging Face's logo

qualcomm
/
MediaPipe-Face-Detection

Object Detection
PyTorch
LiteRT
real_time
android
Model card Files
xet
Community
3
MediaPipe-Face-Detection / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
dcabcc0 verified
preview code
|
raw
history blame
31.3 kB
metadata
library_name: pytorch
license: other
tags:
  - real_time
  - android
pipeline_tag: object-detection

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 parameters (MediaPipeFaceDetector): 135K
    • Model size (MediaPipeFaceDetector): 565 KB
    • Number of parameters (MediaPipeFaceLandmarkDetector): 603K
    • Model size (MediaPipeFaceLandmarkDetector): 2.34 MB
    • Number of output classes: 6
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 2.925 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 2.857 ms 1 - 10 MB NPU Use Export Script
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.872 ms 0 - 22 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.811 ms 1 - 26 MB NPU Use Export Script
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.551 ms 0 - 7 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.535 ms 1 - 3 MB NPU Use Export Script
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.072 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 1.027 ms 1 - 15 MB NPU Use Export Script
FaceDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 2.925 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA7255P ADP Qualcomm® SA7255P QNN 2.857 ms 1 - 10 MB NPU Use Export Script
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.555 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.539 ms 1 - 3 MB NPU Use Export Script
FaceDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 1.144 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8295P ADP Qualcomm® SA8295P QNN 1.03 ms 0 - 20 MB NPU Use Export Script
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.55 ms 0 - 8 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.534 ms 1 - 3 MB NPU Use Export Script
FaceDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 1.072 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8775P ADP Qualcomm® SA8775P QNN 1.027 ms 1 - 15 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.552 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.555 ms 1 - 7 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.835 ms 1 - 7 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.402 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.39 ms 1 - 22 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.598 ms 0 - 22 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.418 ms 0 - 21 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.394 ms 1 - 22 MB NPU Use Export Script
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.686 ms 1 - 1 MB NPU Use Export Script
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.858 ms 2 - 2 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.862 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 0.862 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.335 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.415 ms 0 - 27 MB NPU Use Export Script
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.199 ms 0 - 8 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.216 ms 0 - 3 MB NPU Use Export Script
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.445 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.459 ms 0 - 15 MB NPU Use Export Script
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 0.862 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P QNN 0.862 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.195 ms 0 - 8 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.217 ms 0 - 3 MB NPU Use Export Script
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 0.558 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P QNN 0.573 ms 0 - 18 MB NPU Use Export Script
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.197 ms 0 - 8 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.218 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 0.445 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P QNN 0.459 ms 0 - 15 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.19 ms 0 - 7 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.216 ms 0 - 8 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.379 ms 0 - 7 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.15 ms 0 - 25 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.157 ms 0 - 21 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.287 ms 0 - 25 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.149 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.172 ms 0 - 19 MB NPU Use Export Script
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.298 ms 0 - 0 MB NPU Use Export Script
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.36 ms 0 - 0 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.67 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 0.649 ms 0 - 10 MB NPU Use Export Script
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.345 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.36 ms 0 - 30 MB NPU Use Export Script
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.233 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.225 ms 0 - 2 MB NPU Use Export Script
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.442 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.426 ms 0 - 15 MB NPU Use Export Script
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.608 ms 0 - 26 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 0.633 ms 0 - 14 MB NPU Use Export Script
FaceDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 4.893 ms 0 - 3 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 0.67 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN 0.649 ms 0 - 10 MB NPU Use Export Script
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.233 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.23 ms 0 - 2 MB NPU Use Export Script
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.593 ms 0 - 22 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN 0.545 ms 0 - 6 MB NPU Use Export Script
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.23 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.236 ms 0 - 2 MB NPU Use Export Script
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.442 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN 0.426 ms 0 - 15 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.237 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.238 ms 0 - 12 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.384 ms 0 - 11 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.155 ms 0 - 28 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.155 ms 0 - 24 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.27 ms 0 - 32 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.16 ms 0 - 22 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.135 ms 0 - 23 MB NPU Use Export Script
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.281 ms 0 - 25 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.328 ms 0 - 0 MB NPU Use Export Script
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.371 ms 1 - 1 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.509 ms 0 - 13 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 0.48 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.262 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.27 ms 0 - 20 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.161 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.156 ms 0 - 3 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.355 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.321 ms 0 - 15 MB NPU Use Export Script
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.368 ms 0 - 20 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 0.383 ms 0 - 11 MB NPU Use Export Script
FaceLandmarkDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 2.601 ms 0 - 2 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 0.509 ms 0 - 13 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN 0.48 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.163 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.148 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.515 ms 0 - 22 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN 0.461 ms 0 - 18 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.162 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.156 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.355 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN 0.321 ms 0 - 15 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.153 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.154 ms 0 - 11 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.302 ms 0 - 8 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.109 ms 0 - 24 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.115 ms 0 - 22 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.206 ms 0 - 26 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.123 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.134 ms 0 - 18 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.249 ms 0 - 22 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.227 ms 0 - 0 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.307 ms 0 - 0 MB NPU MediaPipe-Face-Detection.onnx

Installation

Install the package via pip:

pip install qai-hub-models

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub 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

Profiling Results
------------------------------------------------------------
FaceDetector
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 0.7                                  
Estimated peak memory usage (MB): [0, 16]                              
Total # Ops                     : 114                                  
Compute Unit(s)                 : npu (114 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
FaceLandmarkDetector
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 0.5                                  
Estimated peak memory usage (MB): [0, 13]                              
Total # Ops                     : 108                                  
Compute Unit(s)                 : npu (108 ops) gpu (0 ops) cpu (0 ops)

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 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.

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. Sign up for access.

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on MediaPipe-Face-Detection'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