Hugging Face's logo

qualcomm
/
BEVFusion

Other
PyTorch
android
Model card Files
xet
Community

BEVFusion: Optimized for Mobile Deployment

Construct a bird’s eye view from sensors mounted on a vehicle

BeVFusion is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.

This model is an implementation of BEVFusion found here.

This repository provides scripts to run BEVFusion on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Model_use_case.driver_assistance
  • Model Stats:
    • Model checkpoint: camera-only-det.pth
    • Input resolution: 1 x 6 x 3 x 256 x 704
    • Number of parameters: 44M
    • Model size: 171 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
BEVFusionEncoder1 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 708.238 ms 0 - 9 MB NPU Use Export Script
BEVFusionEncoder1 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 525.75 ms 12 - 32 MB NPU Use Export Script
BEVFusionEncoder1 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 618.867 ms 32 - 52 MB NPU Use Export Script
BEVFusionEncoder1 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 426.634 ms 12 - 29 MB NPU Use Export Script
BEVFusionEncoder1 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 509.758 ms 20 - 35 MB NPU Use Export Script
BEVFusionEncoder1 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 361.572 ms 14 - 26 MB NPU Use Export Script
BEVFusionEncoder1 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 432.524 ms 48 - 59 MB NPU Use Export Script
BEVFusionEncoder1 float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 691.279 ms 12 - 12 MB NPU Use Export Script
BEVFusionEncoder1 float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 827.021 ms 97 - 97 MB NPU Use Export Script
BEVFusionEncoder2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 3232.534 ms 1 - 12 MB NPU Use Export Script
BEVFusionEncoder2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 2576.966 ms 10 - 26 MB NPU Use Export Script
BEVFusionEncoder2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 2577.387 ms 603 - 622 MB NPU Use Export Script
BEVFusionEncoder2 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 2364.562 ms 36 - 53 MB NPU Use Export Script
BEVFusionEncoder2 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 2385.21 ms 363 - 378 MB NPU Use Export Script
BEVFusionEncoder2 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 2085.74 ms 17 - 27 MB NPU Use Export Script
BEVFusionEncoder2 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 2106.508 ms 432 - 442 MB NPU Use Export Script
BEVFusionEncoder2 float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 3353.63 ms 17 - 17 MB NPU Use Export Script
BEVFusionEncoder2 float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 3246.258 ms 1058 - 1058 MB NPU Use Export Script
BEVFusionEncoder3 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 719.618 ms 609 - 619 MB NPU Use Export Script
BEVFusionEncoder3 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 590.193 ms 609 - 628 MB NPU Use Export Script
BEVFusionEncoder3 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 455.06 ms 588 - 608 MB NPU Use Export Script
BEVFusionEncoder3 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 507.97 ms 609 - 631 MB NPU Use Export Script
BEVFusionEncoder3 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 375.86 ms 563 - 577 MB NPU Use Export Script
BEVFusionEncoder3 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 374.426 ms 609 - 619 MB NPU Use Export Script
BEVFusionEncoder3 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 332.706 ms 602 - 616 MB NPU Use Export Script
BEVFusionEncoder3 float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 701.353 ms 610 - 610 MB NPU Use Export Script
BEVFusionEncoder3 float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 514.489 ms 610 - 610 MB NPU Use Export Script
BEVFusionEncoder4 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 14.617 ms 18 - 28 MB NPU Use Export Script
BEVFusionEncoder4 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 8.893 ms 18 - 37 MB NPU Use Export Script
BEVFusionEncoder4 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 9.41 ms 32 - 52 MB NPU Use Export Script
BEVFusionEncoder4 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 7.792 ms 10 - 23 MB NPU Use Export Script
BEVFusionEncoder4 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 8.054 ms 11 - 22 MB NPU Use Export Script
BEVFusionEncoder4 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 6.816 ms 18 - 29 MB NPU Use Export Script
BEVFusionEncoder4 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 7.099 ms 31 - 41 MB NPU Use Export Script
BEVFusionEncoder4 float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 11.815 ms 19 - 19 MB NPU Use Export Script
BEVFusionEncoder4 float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 12.059 ms 19 - 19 MB NPU Use Export Script
BEVFusionDecoder float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 23.669 ms 1 - 11 MB NPU Use Export Script
BEVFusionDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 9.665 ms 5 - 23 MB NPU Use Export Script
BEVFusionDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 9.934 ms 15 - 34 MB NPU Use Export Script
BEVFusionDecoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 7.628 ms 5 - 19 MB NPU Use Export Script
BEVFusionDecoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 7.928 ms 12 - 25 MB NPU Use Export Script
BEVFusionDecoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 5.732 ms 5 - 16 MB NPU Use Export Script
BEVFusionDecoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 6.197 ms 14 - 25 MB NPU Use Export Script
BEVFusionDecoder float Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 13.143 ms 5 - 5 MB NPU Use Export Script
BEVFusionDecoder float Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 13.322 ms 23 - 23 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[bevfusion-det]"

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.bevfusion_det.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.bevfusion_det.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.bevfusion_det.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.bevfusion_det 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 (.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 BEVFusion's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of BEVFusion 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
Other
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support