--- library_name: pytorch license: unknown tags: - real_time - android pipeline_tag: image-segmentation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bgnet/web-assets/model_demo.png) # 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](https://github.com/thograce/bgnet). This repository provides scripts to run BGNet on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/bgnet). **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 | 112.395 ms | 1 - 255 MB | NPU | -- | | BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 114.931 ms | 2 - 199 MB | NPU | -- | | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 37.051 ms | 1 - 381 MB | NPU | -- | | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 38.697 ms | 2 - 233 MB | NPU | -- | | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 19.189 ms | 1 - 3 MB | NPU | -- | | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.135 ms | 2 - 4 MB | NPU | -- | | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 18.84 ms | 0 - 161 MB | NPU | -- | | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 31.423 ms | 1 - 254 MB | NPU | -- | | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 32.299 ms | 2 - 200 MB | NPU | -- | | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 112.395 ms | 1 - 255 MB | NPU | -- | | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 114.931 ms | 2 - 199 MB | NPU | -- | | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 32.906 ms | 1 - 226 MB | NPU | -- | | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 34.016 ms | 2 - 169 MB | NPU | -- | | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 31.423 ms | 1 - 254 MB | NPU | -- | | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 32.299 ms | 2 - 200 MB | NPU | -- | | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 13.713 ms | 0 - 408 MB | NPU | -- | | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.488 ms | 2 - 276 MB | NPU | -- | | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.63 ms | 3 - 246 MB | NPU | -- | | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.113 ms | 1 - 252 MB | NPU | -- | | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 11.619 ms | 2 - 201 MB | NPU | -- | | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 11.025 ms | 3 - 175 MB | NPU | -- | | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 8.347 ms | 1 - 264 MB | NPU | -- | | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 8.84 ms | 2 - 209 MB | NPU | -- | | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 10.864 ms | 3 - 183 MB | NPU | -- | | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 20.675 ms | 2 - 2 MB | NPU | -- | | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.138 ms | 154 - 154 MB | NPU | -- | ## Installation Install the package via pip: ```bash # NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported. pip install pysodmetrics==1.5.1 --no-deps pip install "qai-hub-models[bgnet]" ``` ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) 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. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://workbench.aihub.qualcomm.com/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. ```bash 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. ```bash python -m qai_hub_models.models.bgnet.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/bgnet/qai_hub_models/models/BGNet/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) 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. ```python 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 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. ```python 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. ```python 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](https://myaccount.qualcomm.com/signup). ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash 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](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) 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](https://aihub.qualcomm.com/models/bgnet). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## References * [BGNet: Boundary-Guided Camouflaged Object Detection (IJCAI 2022)](https://arxiv.org/abs/2207.00794) * [Source Model Implementation](https://github.com/thograce/bgnet) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).