v0.46.1

See https://github.com/quic/ai-hub-models/releases/v0.46.1 for changelog.

HRNet-W48-OCR_float.onnx.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8bb57bb42fb07409d3e51dfbf71d572c8e8e8da670b8ce19db9ef2f317d85de8
-size 263264360

README.md

@@ -11,212 +11,72 @@ 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: Optimized for Qualcomm Devices
 
 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) | ONNX | 1213.662 ms | 0 - 168 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 | ONNX | 854.428 ms | 25 - 3970 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 S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 741.79 ms | 12 - 2504 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 Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 637.57 ms | 35 - 2596 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 | ONNX | 989.637 ms | 150 - 150 MB | NPU | [HRNet-W48-OCR.onnx.zip](https://huggingface.co/qualcomm/HRNet-W48-OCR/blob/main/HRNet-W48-OCR.onnx.zip) |
-
-
-
-
-## Installation
-
-
-Install the package via pip:
-```bash
-# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
-pip install "qai-hub-models[hrnet-w48-ocr]"
-```
-
-
-## 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.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
+This is based on the implementation of HRNet-W48-OCR found [here](https://github.com/HRNet/HRNet-Semantic-Segmentation).
+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/hrnet_w48_ocr) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
-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.
+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.
 
-```bash
-python -m qai_hub_models.models.hrnet_w48_ocr.export
-```
+## Getting Started
+There are two ways to deploy this model on your device:
 
+### Option 1: Download Pre-Exported Models
 
+Below are pre-exported model assets ready for deployment.
 
-## How does this work?
+| Runtime | Precision | Chipset | SDK Versions | Download |
+|---|---|---|---|---|
+| ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.46.1/hrnet_w48_ocr-onnx-float.zip)
+| QNN_DLC | w8a16 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.46.1/hrnet_w48_ocr-qnn_dlc-w8a16.zip)
+| TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.46.1/hrnet_w48_ocr-tflite-float.zip)
 
-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:
+For more device-specific assets and performance metrics, visit **[HRNet-W48-OCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_w48_ocr)**.
 
-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.
+### Option 2: Export with Custom Configurations
 
-```python
-import torch
+Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/hrnet_w48_ocr) 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
 
-import qai_hub as hub
-from qai_hub_models.models.hrnet_w48_ocr import Model
+This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-# Load the model
-torch_model = Model.from_pretrained()
+See our repository for [HRNet-W48-OCR on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/hrnet_w48_ocr) for usage instructions.
 
-# Device
-device = hub.Device("Samsung Galaxy S25")
+## Model Details
 
-# Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+**Model Type:** Model_use_case.semantic_segmentation
 
-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).
-
-
-
-
-## 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/)
+**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
 
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
+|---|---|---|---|---|---|---
+| HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 990.193 ms | 150 - 150 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 868.977 ms | 36 - 3980 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1168.136 ms | 24 - 28 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® QCS9075 | 1384.373 ms | 24 - 51 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 736.445 ms | 11 - 2506 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 651.912 ms | 37 - 2597 MB | NPU
 
 ## 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).
 
-
-
 ## 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).
-
-

tool-versions.yaml

@@ -1,4 +0,0 @@
-tool_versions:
-  onnx:
-    qairt: 2.37.1.250807093845_124904
-    onnx_runtime: 1.23.0