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

---

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

# GoogLeNet: Optimized for Qualcomm Devices

GoogLeNet 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 GoogLeNet found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.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/qai_hub_models/models/googlenet) 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 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet/releases/v0.48.0/googlenet-tflite-w8a8.zip)

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


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/googlenet) 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 [GoogLeNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/googlenet) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 6.62M
- Model size (float): 25.3 MB
- Model size (w8a8): 6.54 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| GoogLeNet | ONNX | float | Snapdragon® X2 Elite | 0.442 ms | 13 - 13 MB | NPU
| GoogLeNet | ONNX | float | Snapdragon® X Elite | 1.002 ms | 13 - 13 MB | NPU
| GoogLeNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.562 ms | 0 - 46 MB | NPU
| GoogLeNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.843 ms | 0 - 2 MB | NPU
| GoogLeNet | ONNX | float | Qualcomm® QCS9075 | 1.545 ms | 1 - 3 MB | NPU
| GoogLeNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.479 ms | 0 - 31 MB | NPU
| GoogLeNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.398 ms | 0 - 31 MB | NPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.177 ms | 7 - 7 MB | NPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® X Elite | 0.405 ms | 7 - 7 MB | NPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.231 ms | 0 - 54 MB | NPU
| GoogLeNet | ONNX | w8a8 | Qualcomm® QCS6490 | 13.691 ms | 8 - 18 MB | CPU
| GoogLeNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.303 ms | 0 - 9 MB | NPU
| GoogLeNet | ONNX | w8a8 | Qualcomm® QCS9075 | 0.435 ms | 0 - 3 MB | NPU
| GoogLeNet | ONNX | w8a8 | Qualcomm® QCM6690 | 9.199 ms | 7 - 16 MB | CPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.19 ms | 0 - 30 MB | NPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 7.061 ms | 7 - 16 MB | CPU
| GoogLeNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.186 ms | 0 - 34 MB | NPU
| GoogLeNet | QNN_DLC | float | Snapdragon® X2 Elite | 0.502 ms | 1 - 1 MB | NPU
| GoogLeNet | QNN_DLC | float | Snapdragon® X Elite | 0.96 ms | 1 - 1 MB | NPU
| GoogLeNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.552 ms | 0 - 45 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.975 ms | 1 - 28 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.809 ms | 1 - 80 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® SA8775P | 1.542 ms | 1 - 29 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® QCS9075 | 1.517 ms | 3 - 5 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.764 ms | 0 - 45 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® SA7255P | 4.975 ms | 1 - 28 MB | NPU
| GoogLeNet | QNN_DLC | float | Qualcomm® SA8295P | 1.783 ms | 0 - 25 MB | NPU
| GoogLeNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.452 ms | 0 - 31 MB | NPU
| GoogLeNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.381 ms | 1 - 32 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.231 ms | 0 - 0 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.352 ms | 0 - 0 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.181 ms | 0 - 42 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.049 ms | 2 - 4 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.817 ms | 0 - 27 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.249 ms | 0 - 2 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.413 ms | 0 - 29 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.334 ms | 2 - 4 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 2.259 ms | 0 - 29 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.413 ms | 0 - 43 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.817 ms | 0 - 27 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.601 ms | 0 - 25 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.151 ms | 0 - 27 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.328 ms | 0 - 28 MB | NPU
| GoogLeNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.143 ms | 0 - 30 MB | NPU
| GoogLeNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.549 ms | 0 - 59 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.981 ms | 0 - 34 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.809 ms | 0 - 2 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® SA8775P | 1.547 ms | 0 - 37 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® QCS9075 | 1.527 ms | 0 - 16 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.758 ms | 0 - 57 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® SA7255P | 4.981 ms | 0 - 34 MB | NPU
| GoogLeNet | TFLITE | float | Qualcomm® SA8295P | 1.789 ms | 0 - 32 MB | NPU
| GoogLeNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.455 ms | 0 - 38 MB | NPU
| GoogLeNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.384 ms | 0 - 38 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.189 ms | 0 - 41 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.033 ms | 0 - 8 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.828 ms | 0 - 27 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.241 ms | 0 - 2 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® SA8775P | 0.436 ms | 0 - 28 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.347 ms | 0 - 9 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.241 ms | 0 - 28 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.422 ms | 0 - 42 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® SA7255P | 0.828 ms | 0 - 27 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Qualcomm® SA8295P | 0.632 ms | 0 - 24 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.151 ms | 0 - 27 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.332 ms | 0 - 28 MB | NPU
| GoogLeNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.139 ms | 0 - 30 MB | NPU

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

## References
* [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.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).