qualcomm
/

BGNet

@@ -1,6 +1,6 @@
 ---
 library_name: pytorch
-license: unknown
 tags:
 - real_time
 - android
@@ -10,230 +10,111 @@ 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/)
@@ -241,10 +122,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 * [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).

 ---
 library_name: pytorch
+license: other
 tags:
 - real_time
 - android
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bgnet/web-assets/model_demo.png)
+# BGNet: Optimized for Qualcomm Devices
 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 is based on the implementation of BGNet found [here](https://github.com/thograce/bgnet).
+This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/bgnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
+Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
+## Getting Started
+Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
+Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/bgnet) Python library to compile and export the model with your own:
+- Custom weights (e.g., fine-tuned checkpoints)
+- Custom input shapes
+- Target device and runtime configurations
+See our repository for [BGNet on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/bgnet) for usage instructions.
+## 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
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
+|---|---|---|---|---|---|---
+| BGNet | ONNX | float | Snapdragon® X Elite | 19.133 ms | 154 - 154 MB | NPU
+| BGNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 13.733 ms | 3 - 249 MB | NPU
+| BGNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 18.77 ms | 0 - 161 MB | NPU
+| BGNet | ONNX | float | Qualcomm® QCS9075 | 34.55 ms | 2 - 7 MB | NPU
+| BGNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.969 ms | 3 - 176 MB | NPU
+| BGNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.206 ms | 1 - 182 MB | NPU
+| BGNet | ONNX | w8a16 | Snapdragon® X Elite | 12.075 ms | 78 - 78 MB | NPU
+| BGNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 8.779 ms | 2 - 352 MB | NPU
+| BGNet | ONNX | w8a16 | Qualcomm® QCS6490 | 2710.461 ms | 327 - 384 MB | CPU
+| BGNet | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 11.98 ms | 0 - 561 MB | NPU
+| BGNet | ONNX | w8a16 | Qualcomm® QCS9075 | 14.447 ms | 1 - 4 MB | NPU
+| BGNet | ONNX | w8a16 | Qualcomm® QCM6690 | 1254.75 ms | 267 - 282 MB | CPU
+| BGNet | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.96 ms | 2 - 214 MB | NPU
+| BGNet | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1251.117 ms | 220 - 231 MB | CPU
+| BGNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 5.159 ms | 0 - 214 MB | NPU
+| BGNet | ONNX | w8a8 | Snapdragon® X Elite | 6.222 ms | 78 - 78 MB | NPU
+| BGNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 4.466 ms | 0 - 281 MB | NPU
+| BGNet | ONNX | w8a8 | Qualcomm® QCS6490 | 446.974 ms | 49 - 158 MB | CPU
+| BGNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 6.373 ms | 0 - 83 MB | NPU
+| BGNet | ONNX | w8a8 | Qualcomm® QCS9075 | 7.517 ms | 0 - 4 MB | NPU
+| BGNet | ONNX | w8a8 | Qualcomm® QCM6690 | 395.944 ms | 52 - 68 MB | CPU
+| BGNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.796 ms | 0 - 177 MB | NPU
+| BGNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 328.101 ms | 28 - 40 MB | CPU
+| BGNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.095 ms | 0 - 178 MB | NPU
+| BGNet | QNN_DLC | float | Snapdragon® X Elite | 20.02 ms | 2 - 2 MB | NPU
+| BGNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 14.126 ms | 0 - 310 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 115.222 ms | 2 - 238 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 19.65 ms | 2 - 4 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® SA8775P | 31.764 ms | 2 - 237 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® QCS9075 | 37.248 ms | 2 - 6 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 39.088 ms | 0 - 260 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® SA7255P | 115.222 ms | 2 - 238 MB | NPU
+| BGNet | QNN_DLC | float | Qualcomm® SA8295P | 34.339 ms | 2 - 195 MB | NPU
+| BGNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 11.059 ms | 2 - 234 MB | NPU
+| BGNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.697 ms | 2 - 245 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Snapdragon® X Elite | 12.967 ms | 1 - 1 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.094 ms | 0 - 393 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 61.717 ms | 1 - 4 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 36.589 ms | 1 - 259 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 12.406 ms | 1 - 3 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® SA8775P | 12.83 ms | 1 - 260 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 15.088 ms | 1 - 4 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 200.187 ms | 1 - 362 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 20.716 ms | 1 - 377 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® SA7255P | 36.589 ms | 1 - 259 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Qualcomm® SA8295P | 20.431 ms | 1 - 258 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.88 ms | 1 - 251 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 23.422 ms | 1 - 340 MB | NPU
+| BGNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 5.914 ms | 1 - 258 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 6.449 ms | 0 - 0 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 4.419 ms | 0 - 318 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 26.543 ms | 2 - 5 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 17.966 ms | 1 - 212 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 6.205 ms | 1 - 2 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 6.601 ms | 1 - 214 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 7.502 ms | 1 - 3 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 112.998 ms | 1 - 290 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 9.531 ms | 0 - 318 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 17.966 ms | 1 - 212 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 10.032 ms | 1 - 214 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.577 ms | 0 - 211 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 11.111 ms | 1 - 285 MB | NPU
+| BGNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 2.843 ms | 1 - 215 MB | NPU
+| BGNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 14.439 ms | 1 - 457 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 113.713 ms | 1 - 301 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 19.606 ms | 1 - 4 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® SA8775P | 31.741 ms | 1 - 303 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® QCS9075 | 34.936 ms | 1 - 159 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 37.065 ms | 1 - 415 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® SA7255P | 113.713 ms | 1 - 301 MB | NPU
+| BGNet | TFLITE | float | Qualcomm® SA8295P | 32.914 ms | 1 - 261 MB | NPU
+| BGNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 11.381 ms | 0 - 300 MB | NPU
+| BGNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.535 ms | 1 - 311 MB | NPU
 * [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).