--- library_name: pytorch license: other tags: - real_time - android pipeline_tag: image-segmentation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bisenet/web-assets/model_demo.png) # BiseNet: Optimized for Mobile Deployment ## Segment images or video by class in real-time on device BiSeNet (Bilateral Segmentation Network) is a novel architecture designed for real-time semantic segmentation. It addresses the challenge of balancing spatial resolution and receptive field by employing a Spatial Path to preserve high-resolution features and a context path to capture sufficient receptive field. This model is an implementation of BiseNet found [here](https://github.com/ooooverflow/BiSeNet). This repository provides scripts to run BiseNet on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/bisenet). ### Model Details - **Model Type:** Model_use_case.semantic_segmentation - **Model Stats:** - Model checkpoint: best_dice_loss_miou_0.655.pth - Inference latency: RealTime - Input resolution: 720x960 - Number of parameters: 12.0M - Model size (float): 45.7 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | BiseNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 105.14 ms | 32 - 195 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 105.598 ms | 2 - 163 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 55.562 ms | 32 - 278 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 56.142 ms | 8 - 252 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 27.367 ms | 32 - 35 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 27.633 ms | 8 - 10 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 32.615 ms | 63 - 86 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.onnx.zip) | | BiseNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 36.987 ms | 32 - 194 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 37.039 ms | 2 - 163 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 105.14 ms | 32 - 195 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 105.598 ms | 2 - 163 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 27.974 ms | 27 - 30 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 27.665 ms | 8 - 10 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 42.839 ms | 32 - 220 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 42.808 ms | 0 - 187 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 28.254 ms | 32 - 38 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 27.615 ms | 8 - 10 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 36.987 ms | 32 - 194 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 37.039 ms | 2 - 163 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 19.493 ms | 31 - 264 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 19.385 ms | 8 - 237 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 26.19 ms | 73 - 269 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.onnx.zip) | | BiseNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 18.526 ms | 31 - 261 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 15.886 ms | 8 - 208 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 19.385 ms | 65 - 205 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.onnx.zip) | | BiseNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 11.724 ms | 30 - 214 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.tflite) | | BiseNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 11.784 ms | 8 - 190 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 15.167 ms | 73 - 220 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.onnx.zip) | | BiseNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 27.498 ms | 8 - 8 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.dlc) | | BiseNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 31.473 ms | 66 - 66 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet.onnx.zip) | | BiseNet | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | TFLITE | 69.16 ms | 6 - 183 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | QNN_DLC | 83.202 ms | 2 - 180 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | ONNX | 232.951 ms | 225 - 239 MB | CPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 40.076 ms | 7 - 31 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | QNN_DLC | 34.191 ms | 2 - 13 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 235.308 ms | 221 - 234 MB | CPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 20.517 ms | 8 - 164 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 20.047 ms | 2 - 157 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.74 ms | 8 - 215 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 16.14 ms | 2 - 204 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 11.826 ms | 8 - 10 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 9.512 ms | 2 - 5 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.616 ms | 16 - 30 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 12.591 ms | 8 - 164 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 10.219 ms | 2 - 158 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 165.644 ms | 37 - 94 MB | GPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 201.932 ms | 211 - 234 MB | CPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 20.517 ms | 8 - 164 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 20.047 ms | 2 - 157 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 11.844 ms | 8 - 10 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 9.497 ms | 1 - 3 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 14.927 ms | 8 - 168 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 12.613 ms | 2 - 161 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 11.839 ms | 8 - 10 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 9.527 ms | 2 - 4 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 12.591 ms | 8 - 164 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 10.219 ms | 2 - 158 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.515 ms | 8 - 213 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.605 ms | 2 - 206 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.989 ms | 18 - 209 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 6.555 ms | 6 - 171 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 5.119 ms | 2 - 163 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.805 ms | 18 - 163 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 14.954 ms | 6 - 177 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 12.695 ms | 2 - 173 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 221.072 ms | 214 - 231 MB | CPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 5.468 ms | 6 - 173 MB | NPU | [BiseNet.tflite](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.tflite) | | BiseNet | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 4.199 ms | 2 - 166 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.775 ms | 0 - 149 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | | BiseNet | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 10.144 ms | 2 - 2 MB | NPU | [BiseNet.dlc](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.dlc) | | BiseNet | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.664 ms | 19 - 19 MB | NPU | [BiseNet.onnx.zip](https://huggingface.co/qualcomm/BiseNet/blob/main/BiseNet_w8a8.onnx.zip) | ## Installation Install the package via pip: ```bash pip install qai-hub-models ``` ## 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.bisenet.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.bisenet.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.bisenet.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/bisenet/qai_hub_models/models/BiseNet/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.bisenet 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.bisenet.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.bisenet.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 BiseNet's performance across various devices [here](https://aihub.qualcomm.com/models/bisenet). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of BiseNet can be found [here](https://github.com/ooooverflow/BiSeNet/pull/45/files). ## References * [BiSeNet Bilateral Segmentation Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1808.00897) * [Source Model Implementation](https://github.com/ooooverflow/BiSeNet) ## 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).