--- datasets: - imagenet-1k - imagenet-22k library_name: pytorch license: bsd-3-clause pipeline_tag: image-classification tags: - quantized - backbone - real_time - android --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large_quantized/web-assets/model_demo.png) # MobileNet-v3-Large-Quantized: Optimized for Mobile Deployment ## Imagenet classifier and general purpose backbone MobileNet-v3-Large 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 model is an implementation of MobileNet-v3-Large-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py). This repository provides scripts to run MobileNet-v3-Large-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/mobilenet_v3_large_quantized). ### Model Details - **Model Type:** Image classification - **Model Stats:** - Model checkpoint: Imagenet - Input resolution: 224x224 - Number of parameters: 5.47M - Model size: 5.79 MB | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model | ---|---|---|---|---|---|---|---| | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.359 ms | 0 - 1 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.622 ms | 0 - 61 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.so](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.so) ## Installation This model can be installed as a Python package via pip. ```bash pip install "qai-hub-models[mobilenet_v3_large_quantized]" ``` ## 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.mobilenet_v3_large_quantized.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.mobilenet_v3_large_quantized.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.mobilenet_v3_large_quantized.export ``` ``` Profile Job summary of MobileNet-v3-Large-Quantized -------------------------------------------------- Device: SA8255 (Proxy) (13) Estimated Inference Time: 0.62 ms Estimated Peak Memory Range: 0.02-11.40 MB Compute Units: NPU (126) | Total (126) ``` ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash python -m qai_hub_models.models.mobilenet_v3_large_quantized.demo --on-device ``` **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.mobilenet_v3_large_quantized.demo -- --on-device ``` ## 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 MobileNet-v3-Large-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/mobilenet_v3_large_quantized). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License - The license for the original implementation of MobileNet-v3-Large-Quantized can be found [here](https://github.com/pytorch/vision/blob/main/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 * [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244) * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py) ## Community * Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) 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).