ConvNext-Tiny-w8a8-Quantized: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

ConvNextTiny 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 ConvNext-Tiny-w8a8-Quantized found here. This repository provides scripts to run ConvNext-Tiny-w8a8-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

• Model Type: Image classification
• Model Stats:
  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 28.6M
  • Model size: 28 MB
  • Precision: w8a8 (8-bit weights, 8-bit activations)

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	QNN Model Library	1.717 ms	0 - 131 MB	INT8	NPU	ConvNext-Tiny-w8a8-Quantized.so

Installation

This model can be installed as a Python package via pip.

pip install "qai-hub-models[convnext_tiny_w8a8_quantized]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub 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.

qai-hub configure --api_token API_TOKEN

Navigate to 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.

python -m qai_hub_models.models.convnext_tiny_w8a8_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.convnext_tiny_w8a8_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.

python -m qai_hub_models.models.convnext_tiny_w8a8_quantized.export

Profile Job summary of ConvNext-Tiny-w8a8-Quantized
--------------------------------------------------
Device: SA8255 (Proxy) (13)
Estimated Inference Time: 1.72 ms
Estimated Peak Memory Range: 0.02-130.98 MB
Compute Units: NPU (215) | Total (215)

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.convnext_tiny_w8a8_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.convnext_tiny_w8a8_quantized.demo -- --on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

• TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

• QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on ConvNext-Tiny-w8a8-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

• The license for the original implementation of ConvNext-Tiny-w8a8-Quantized can be found here.
• The license for the compiled assets for on-device deployment can be found here

References

• A ConvNet for the 2020s
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.