---
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/inception_v3/web-assets/model_demo.png)

# Inception-v3: Optimized for Qualcomm Devices

InceptionNetV3 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 Inception-v3 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.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/inception_v3) 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/inception_v3/releases/v0.53.1/inception_v3-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/inception_v3/releases/v0.53.1/inception_v3-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/inception_v3/releases/v0.53.1/inception_v3-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/inception_v3/releases/v0.53.1/inception_v3-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/inception_v3/releases/v0.53.1/inception_v3-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.53.1/inception_v3-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[Inception-v3 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/inception_v3)**.


### 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/inception_v3) 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 [Inception-v3 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/inception_v3) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 23.9M
- Model size (float): 90.9 MB
- Model size (w8a8): 23.3 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| Inception-v3 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.804 ms | 1 - 39 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.935 ms | 0 - 40 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® X2 Elite | 0.709 ms | 46 - 46 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® X Elite | 1.518 ms | 46 - 46 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® X Elite | 1.52 ms | 46 - 46 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.045 ms | 0 - 56 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.489 ms | 0 - 50 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® QCS9075 | 2.173 ms | 0 - 4 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.942 ms | 0 - 41 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.407 ms | 0 - 57 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.435 ms | 0 - 52 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.288 ms | 23 - 23 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® X Elite | 0.74 ms | 23 - 23 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® X Elite | 0.716 ms | 23 - 23 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.507 ms | 0 - 90 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® QCS6490 | 25.481 ms | 10 - 39 MB | CPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.66 ms | 0 - 27 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® QCS9075 | 0.747 ms | 0 - 3 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® QCM6690 | 17.941 ms | 10 - 20 MB | CPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.432 ms | 0 - 56 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.211 ms | 17 - 27 MB | CPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.035 ms | 15 - 25 MB | CPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.763 ms | 1 - 36 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.881 ms | 1 - 36 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® X2 Elite | 0.76 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® X Elite | 1.409 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® X Elite | 1.426 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.031 ms | 0 - 53 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.825 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.366 ms | 0 - 3 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8775P | 2.24 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8775P | 2.233 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8775P | 2.233 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® QCS9075 | 2.051 ms | 1 - 3 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.344 ms | 0 - 53 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA7255P | 7.825 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8295P | 2.66 ms | 0 - 30 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.89 ms | 1 - 33 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.363 ms | 0 - 51 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.415 ms | 0 - 52 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.349 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.681 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.665 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.478 ms | 0 - 74 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.162 ms | 0 - 2 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.557 ms | 0 - 48 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.622 ms | 0 - 109 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.783 ms | 0 - 52 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.774 ms | 0 - 51 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.774 ms | 0 - 51 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.619 ms | 2 - 4 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 5.765 ms | 0 - 52 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.89 ms | 0 - 75 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.557 ms | 0 - 48 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.139 ms | 0 - 48 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.418 ms | 0 - 48 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.965 ms | 0 - 50 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.958 ms | 0 - 50 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.759 ms | 0 - 67 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.872 ms | 0 - 64 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.026 ms | 0 - 114 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.846 ms | 0 - 64 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.364 ms | 0 - 2 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8775P | 2.257 ms | 0 - 66 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8775P | 2.264 ms | 0 - 65 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8775P | 2.264 ms | 0 - 65 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® QCS9075 | 2.057 ms | 0 - 48 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.354 ms | 0 - 117 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA7255P | 7.846 ms | 0 - 64 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8295P | 2.679 ms | 0 - 62 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.867 ms | 0 - 64 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.377 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.413 ms | 0 - 53 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.478 ms | 0 - 76 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.365 ms | 0 - 25 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.631 ms | 0 - 49 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.638 ms | 0 - 39 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.865 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.861 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.861 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.712 ms | 0 - 25 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCM6690 | 5.864 ms | 0 - 52 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.936 ms | 0 - 78 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.631 ms | 0 - 49 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.256 ms | 0 - 47 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.414 ms | 0 - 48 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.965 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.969 ms | 0 - 51 MB | NPU

## License
* The license for the original implementation of Inception-v3 can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.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).