Hugging Face's logo

qualcomm
/
BGNet

Image Segmentation
PyTorch
real_time
android
Model card Files Community
BGNet / README.md
qaihm-bot's picture
qaihm-bot
v0.36.0
c14e193 verified
preview code
|
raw
history blame contribute delete
10.1 kB
metadata
library_name: pytorch
license: other
tags:
  - real_time
  - android
pipeline_tag: image-segmentation

BGNet: Optimized for Mobile Deployment

Segment images in real-time on device

BGNet or Boundary-Guided Network, is a model designed for camouflaged object detection. It leverages edge semantics to enhance the representation learning process, making it more effective at identifying objects that blend into their surroundings

This model is an implementation of BGNet found here.

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

WARNING: The model assets are not readily available for download due to licensing restrictions.

Model Details

  • Model Type: Model_use_case.semantic_segmentation
  • Model Stats:
    • Model checkpoint: BGNet
    • Input resolution: 416x416
    • Number of parameters: 77.8M
    • Model size (float): 297 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
BGNet float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 117.682 ms 0 - 136 MB NPU --
BGNet float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 117.293 ms 2 - 77 MB NPU --
BGNet float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 33.685 ms 1 - 209 MB NPU --
BGNet float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 37.321 ms 2 - 66 MB NPU --
BGNet float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 22.844 ms 1 - 28 MB NPU --
BGNet float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 20.093 ms 2 - 33 MB NPU --
BGNet float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 34.605 ms 0 - 133 MB NPU --
BGNet float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 32.39 ms 2 - 76 MB NPU --
BGNet float SA7255P ADP Qualcomm® SA7255P TFLITE 117.682 ms 0 - 136 MB NPU --
BGNet float SA7255P ADP Qualcomm® SA7255P QNN_DLC 117.293 ms 2 - 77 MB NPU --
BGNet float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 22.769 ms 1 - 27 MB NPU --
BGNet float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 20.279 ms 2 - 30 MB NPU --
BGNet float SA8295P ADP Qualcomm® SA8295P TFLITE 37.564 ms 1 - 108 MB NPU --
BGNet float SA8295P ADP Qualcomm® SA8295P QNN_DLC 35.763 ms 2 - 54 MB NPU --
BGNet float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 22.655 ms 1 - 27 MB NPU --
BGNet float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 20.126 ms 2 - 29 MB NPU --
BGNet float SA8775P ADP Qualcomm® SA8775P TFLITE 34.605 ms 0 - 133 MB NPU --
BGNet float SA8775P ADP Qualcomm® SA8775P QNN_DLC 32.39 ms 2 - 76 MB NPU --
BGNet float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 22.673 ms 1 - 27 MB NPU --
BGNet float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 20.048 ms 2 - 31 MB NPU --
BGNet float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 20.354 ms 0 - 179 MB NPU --
BGNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 16.761 ms 1 - 222 MB NPU --
BGNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 14.854 ms 2 - 91 MB NPU --
BGNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 14.863 ms 3 - 85 MB NPU --
BGNet float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 15.844 ms 1 - 139 MB NPU --
BGNet float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 13.84 ms 0 - 76 MB NPU --
BGNet float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 15.232 ms 0 - 69 MB NPU --
BGNet float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 20.735 ms 378 - 378 MB NPU --
BGNet float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 21.812 ms 154 - 154 MB NPU --

Installation

Install the package via pip:

pip install "qai-hub-models[bgnet]"

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.bgnet.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.bgnet.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.bgnet.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.bgnet 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.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.bgnet.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.bgnet.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 BGNet's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of BGNet can be found [here](This model's original implementation does not provide a LICENSE.).
  • The license for the compiled assets for on-device deployment can be found here

References

Community