---
library_name: pytorch
license: other
tags:
- backbone
- android
pipeline_tag: image-classification

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/web-assets/model_demo.png)

# WideResNet50: Optimized for Qualcomm Devices

WideResNet50 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of WideResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/wideresnet50) 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
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.

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.52.0/wideresnet50-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[WideResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/wideresnet50)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/wideresnet50) 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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for [WideResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/wideresnet50) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 68.9M
- Model size (float): 263 MB
- Model size (w8a8): 66.6 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| WideResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.64 ms | 1 - 189 MB | NPU
| WideResNet50 | ONNX | float | Snapdragon® X2 Elite | 2.187 ms | 132 - 132 MB | NPU
| WideResNet50 | ONNX | float | Snapdragon® X Elite | 4.439 ms | 132 - 132 MB | NPU
| WideResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.468 ms | 0 - 226 MB | NPU
| WideResNet50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.568 ms | 1 - 366 MB | NPU
| WideResNet50 | ONNX | float | Qualcomm® QCS9075 | 6.776 ms | 1 - 4 MB | NPU
| WideResNet50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.81 ms | 0 - 179 MB | NPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.149 ms | 0 - 53 MB | NPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.819 ms | 66 - 66 MB | NPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 1.788 ms | 66 - 66 MB | NPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.413 ms | 0 - 131 MB | NPU
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS6490 | 77.076 ms | 10 - 111 MB | CPU
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.857 ms | 0 - 99 MB | NPU
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.929 ms | 0 - 3 MB | NPU
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCM6690 | 61.735 ms | 0 - 9 MB | CPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.222 ms | 0 - 54 MB | NPU
| WideResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 57.377 ms | 8 - 16 MB | CPU
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.554 ms | 1 - 171 MB | NPU
| WideResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 2.458 ms | 1 - 1 MB | NPU
| WideResNet50 | QNN_DLC | float | Snapdragon® X Elite | 4.69 ms | 1 - 1 MB | NPU
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.644 ms | 0 - 224 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 24.506 ms | 1 - 174 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.834 ms | 1 - 2 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 7.151 ms | 1 - 169 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 7.097 ms | 1 - 3 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.199 ms | 0 - 197 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 24.506 ms | 1 - 174 MB | NPU
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 7.847 ms | 1 - 153 MB | NPU
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.897 ms | 0 - 175 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.093 ms | 0 - 56 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.899 ms | 0 - 0 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.798 ms | 0 - 0 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.41 ms | 0 - 126 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 7.83 ms | 0 - 2 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 4.02 ms | 0 - 53 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.87 ms | 0 - 2 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.014 ms | 0 - 54 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.914 ms | 0 - 2 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 17.895 ms | 0 - 215 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.518 ms | 0 - 128 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 4.02 ms | 0 - 53 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.754 ms | 0 - 51 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.201 ms | 0 - 54 MB | NPU
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.853 ms | 0 - 210 MB | NPU
| WideResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.513 ms | 0 - 102 MB | NPU
| WideResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.55 ms | 0 - 215 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 23.784 ms | 0 - 100 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.75 ms | 0 - 2 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® SA8775P | 7.04 ms | 0 - 101 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® QCS9075 | 7.057 ms | 0 - 134 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.181 ms | 0 - 191 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® SA7255P | 23.784 ms | 0 - 100 MB | NPU
| WideResNet50 | TFLITE | float | Qualcomm® SA8295P | 7.772 ms | 0 - 88 MB | NPU
| WideResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.848 ms | 0 - 106 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.05 ms | 0 - 57 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.329 ms | 0 - 131 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 6.887 ms | 0 - 68 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.762 ms | 0 - 52 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.732 ms | 0 - 3 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.887 ms | 0 - 53 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.75 ms | 0 - 68 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 17.549 ms | 0 - 214 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.397 ms | 0 - 126 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 3.762 ms | 0 - 52 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 2.572 ms | 0 - 56 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.118 ms | 0 - 53 MB | NPU
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.72 ms | 0 - 208 MB | NPU

## License
* The license for the original implementation of WideResNet50 can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)

## 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).