Hugging Face's logo

qualcomm
/
CenterNet-2D

Object Detection
PyTorch
android
Model card Files
xet
Community

CenterNet-2D: Optimized for Mobile Deployment

Object Detection

CenterNet-2D is machine learning model that detects objects by finding their center points.

This model is an implementation of CenterNet-2D found here.

This repository provides scripts to run CenterNet-2D 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:
    • Model checkpoint: ctdet_coco_dla_2x.pth
    • Input resolution: 1 x 3 x 512 x 512
    • Number of parameters: 20.2M
    • Model size: 37.6 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
CenterNet-2D float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_CONTEXT_BINARY 553.912 ms 3 - 13 MB NPU Use Export Script
CenterNet-2D float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_CONTEXT_BINARY 730.258 ms 4 - 24 MB NPU Use Export Script
CenterNet-2D float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_CONTEXT_BINARY 428.708 ms 3 - 5 MB NPU Use Export Script
CenterNet-2D float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) PRECOMPILED_QNN_ONNX 398.074 ms 0 - 63 MB NPU Use Export Script
CenterNet-2D float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 421.391 ms 1 - 11 MB NPU Use Export Script
CenterNet-2D float SA7255P ADP Qualcomm® SA7255P QNN_CONTEXT_BINARY 553.912 ms 3 - 13 MB NPU Use Export Script
CenterNet-2D float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_CONTEXT_BINARY 429.888 ms 3 - 5 MB NPU Use Export Script
CenterNet-2D float SA8295P ADP Qualcomm® SA8295P QNN_CONTEXT_BINARY 482.626 ms 0 - 16 MB NPU Use Export Script
CenterNet-2D float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_CONTEXT_BINARY 431.621 ms 3 - 6 MB NPU Use Export Script
CenterNet-2D float SA8775P ADP Qualcomm® SA8775P QNN_CONTEXT_BINARY 421.391 ms 1 - 11 MB NPU Use Export Script
CenterNet-2D float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 317.413 ms 3 - 22 MB NPU Use Export Script
CenterNet-2D float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 291.555 ms 16 - 34 MB NPU Use Export Script
CenterNet-2D float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 288.71 ms 3 - 20 MB NPU Use Export Script
CenterNet-2D float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 290.218 ms 14 - 25 MB NPU Use Export Script
CenterNet-2D float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 250.803 ms 3 - 14 MB NPU Use Export Script
CenterNet-2D float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 410.85 ms 3 - 3 MB NPU Use Export Script
CenterNet-2D float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 385.083 ms 56 - 56 MB NPU Use Export Script

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[centernet-2d]"

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.centernet_2d.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.centernet_2d.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.centernet_2d.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.centernet_2d 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. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.centernet_2d.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.centernet_2d.demo -- --eval-mode on-device

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 CenterNet-2D's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of CenterNet-2D can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support