Hugging Face's logo

qualcomm
/
ResNet101Quantized

Image Classification
PyTorch
TF Lite
backbone
quantized
android
Model card Files Community
ResNet101Quantized / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
b5ad585 verified
preview code
|
raw
history blame
No virus
5.58 kB
metadata
datasets:
  - imagenet-1k
  - imagenet-22k
library_name: pytorch
license: bsd-3-clause
pipeline_tag: image-classification
tags:
  - backbone
  - quantized
  - android

ResNet101Quantized: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

ResNet101 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 ResNet101Quantized found here. This repository provides scripts to run ResNet101Quantized 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: 44.5M
    • Model size: 43.9 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 1.188 ms 0 - 2 MB INT8 NPU ResNet101Quantized.tflite
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 QNN Model Library 1.377 ms 0 - 56 MB INT8 NPU ResNet101Quantized.so

Installation

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

pip install "qai-hub-models[resnet101_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.resnet101_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.resnet101_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.resnet101_quantized.export

Profile Job summary of ResNet101Quantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 1.38 ms
Estimated Peak Memory Range: 0.26-0.26 MB
Compute Units: NPU (146) | Total (146)

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.resnet101_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.resnet101_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 ResNet101Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of ResNet101Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community