Simple-Bev: Optimized for Mobile Deployment

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

Simple_bev is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle. It uses the ResNet-101 as the backbone and segnet as a segmentation model for specific use cases.

This model is an implementation of Simple-Bev found here.

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

Model Details

Model Type: Image generation
Model Stats:
- Model checkpoint: model-000025000.pth
- Input resolution: 448 x 800
- Number of parameters: 42M
- Model size: 505 MB

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
Simple-Bev	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	1533.805 ms	1235 - 1552 MB	FP32	CPU	Simple-Bev.tflite
Simple-Bev	SA8295P ADP	SA8295P	TFLITE	1908.015 ms	1249 - 1560 MB	FP32	CPU	Simple-Bev.tflite
Simple-Bev	SA8775P ADP	SA8775P	TFLITE	3593.07 ms	1249 - 1546 MB	FP32	CPU	Simple-Bev.tflite
Simple-Bev	QCS9075 (Proxy)	QCS9075 Proxy	TFLITE	3593.07 ms	1249 - 1546 MB	FP32	CPU	Simple-Bev.tflite

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.simple_bev_cam.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.simple_bev_cam.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.simple_bev_cam.export

Profiling Results
------------------------------------------------------------
Simple-Bev
Device                          : Snapdragon 8 Elite QRD (15)
Runtime                         : TFLITE                     
Estimated inference time (ms)   : 1533.8                     
Estimated peak memory usage (MB): [1235, 1552]               
Total # Ops                     : 397                        
Compute Unit(s)                 : GPU (191 ops) CPU (206 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.simple_bev_cam 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 Simple-Bev's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

The license for the original implementation of Simple-Bev 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.