--- 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/hrnet_w48_ocr/web-assets/model_demo.png) # HRNet-W48-OCR: Optimized for Mobile Deployment ## Semantic segmentation in higher resolution HRNet-W48-OCR is a machine learning model that can segment images from the Cityscape dataset. It has lightweight and hardware-efficient operations and thus delivers significant speedup on diverse hardware platforms This model is an implementation of HRNet-W48-OCR found [here](https://github.com/HRNet/HRNet-Semantic-Segmentation). This repository provides scripts to run HRNet-W48-OCR on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/hrnet_w48_ocr). ### Model Details - **Model Type:** Model_use_case.semantic_segmentation - **Model Stats:** - Model checkpoint: hrnet_ocr_cs_8162_torch11.pth - Input resolution: 2048x1024 - Number of output classes: 19 - Number of parameters: 70.3M - Model size (float): 268 MB - Model size (w8a16): 70.3 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | HRNet-W48-OCR | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1282.606 ms | 0 - 98 MB | NPU | [HRNet-W48-OCR.tflite](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.tflite) | | HRNet-W48-OCR | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1220.428 ms | 24 - 108 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.dlc) | | HRNet-W48-OCR | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 1267.452 ms | 0 - 238 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) | | HRNet-W48-OCR | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1279.616 ms | 0 - 74 MB | NPU | [HRNet-W48-OCR.tflite](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.tflite) | | HRNet-W48-OCR | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 1224.427 ms | 24 - 112 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.dlc) | | HRNet-W48-OCR | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1310.401 ms | 0 - 245 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) | | HRNet-W48-OCR | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 944.714 ms | 0 - 2169 MB | NPU | [HRNet-W48-OCR.tflite](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.tflite) | | HRNet-W48-OCR | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 910.73 ms | 24 - 2266 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.dlc) | | HRNet-W48-OCR | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 960.662 ms | 24 - 1874 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) | | HRNet-W48-OCR | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 843.357 ms | 0 - 2154 MB | NPU | [HRNet-W48-OCR.tflite](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.tflite) | | HRNet-W48-OCR | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 870.903 ms | 24 - 2333 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.dlc) | | HRNet-W48-OCR | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 870.401 ms | 25 - 1919 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) | | HRNet-W48-OCR | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1146.046 ms | 219 - 219 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.dlc) | | HRNet-W48-OCR | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1145.728 ms | 146 - 146 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) | | HRNet-W48-OCR | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8746.15 ms | 12 - 929 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8466.877 ms | 12 - 140 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7667.801 ms | 12 - 766 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8583.983 ms | 12 - 141 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6616.52 ms | 12 - 714 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 8292.519 ms | 12 - 828 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | | HRNet-W48-OCR | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8562.506 ms | 192 - 192 MB | NPU | [HRNet-W48-OCR.dlc](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR_w8a16.dlc) | ## Installation Install the package via pip: ```bash pip install "qai-hub-models[hrnet-w48-ocr]" ``` ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub](https://app.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://app.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.hrnet_w48_ocr.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.hrnet_w48_ocr.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.hrnet_w48_ocr.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/hrnet_w48_ocr/qai_hub_models/models/HRNet-W48-OCR/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.hrnet_w48_ocr 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. ```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. [Sign up for access](https://myaccount.qualcomm.com/signup). ## 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 HRNet-W48-OCR's performance across various devices [here](https://aihub.qualcomm.com/models/hrnet_w48_ocr). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of HRNet-W48-OCR can be found [here](https://github.com/HRNet/HRNet-Semantic-Segmentation/blob/HRNet-OCR/LICENSE). * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) ## References * [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/abs/1909.11065) * [Source Model Implementation](https://github.com/HRNet/HRNet-Semantic-Segmentation) ## 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).