WideResNet50: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

WideResNet50 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 WideResNet50 found here.

This repository provides scripts to run WideResNet50 on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Model_use_case.image_classification
  • Model Stats:
    • Model checkpoint: Imagenet
    • Input resolution: 224x224
    • Number of parameters: 68.8M
    • Model size (float): 263 MB
    • Model size (w8a8): 66.6 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
WideResNet50 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 24.353 ms 0 - 83 MB NPU WideResNet50.tflite
WideResNet50 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 24.437 ms 1 - 10 MB NPU Use Export Script
WideResNet50 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 7.175 ms 0 - 174 MB NPU WideResNet50.tflite
WideResNet50 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 9.939 ms 1 - 37 MB NPU Use Export Script
WideResNet50 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 4.894 ms 0 - 1029 MB NPU WideResNet50.tflite
WideResNet50 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 4.901 ms 1 - 4 MB NPU Use Export Script
WideResNet50 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 7.449 ms 0 - 83 MB NPU WideResNet50.tflite
WideResNet50 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 7.191 ms 1 - 12 MB NPU Use Export Script
WideResNet50 float SA7255P ADP Qualcomm® SA7255P TFLITE 24.353 ms 0 - 83 MB NPU WideResNet50.tflite
WideResNet50 float SA7255P ADP Qualcomm® SA7255P QNN 24.437 ms 1 - 10 MB NPU Use Export Script
WideResNet50 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 4.909 ms 0 - 834 MB NPU WideResNet50.tflite
WideResNet50 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 4.942 ms 1 - 4 MB NPU Use Export Script
WideResNet50 float SA8295P ADP Qualcomm® SA8295P TFLITE 7.981 ms 0 - 80 MB NPU WideResNet50.tflite
WideResNet50 float SA8295P ADP Qualcomm® SA8295P QNN 7.66 ms 1 - 18 MB NPU Use Export Script
WideResNet50 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 4.898 ms 0 - 1003 MB NPU WideResNet50.tflite
WideResNet50 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 4.919 ms 1 - 3 MB NPU Use Export Script
WideResNet50 float SA8775P ADP Qualcomm® SA8775P TFLITE 7.449 ms 0 - 83 MB NPU WideResNet50.tflite
WideResNet50 float SA8775P ADP Qualcomm® SA8775P QNN 7.191 ms 1 - 12 MB NPU Use Export Script
WideResNet50 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 4.9 ms 0 - 1030 MB NPU WideResNet50.tflite
WideResNet50 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 4.949 ms 1 - 10 MB NPU Use Export Script
WideResNet50 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 4.839 ms 0 - 297 MB NPU WideResNet50.onnx
WideResNet50 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 3.639 ms 0 - 174 MB NPU WideResNet50.tflite
WideResNet50 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 3.783 ms 0 - 40 MB NPU Use Export Script
WideResNet50 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 3.795 ms 1 - 39 MB NPU WideResNet50.onnx
WideResNet50 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 3.028 ms 0 - 88 MB NPU WideResNet50.tflite
WideResNet50 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 3.369 ms 1 - 37 MB NPU Use Export Script
WideResNet50 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 3.506 ms 0 - 36 MB NPU WideResNet50.onnx
WideResNet50 float Snapdragon X Elite CRD Snapdragon® X Elite QNN 4.774 ms 1 - 1 MB NPU Use Export Script
WideResNet50 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 4.464 ms 133 - 133 MB NPU WideResNet50.onnx
WideResNet50 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3.847 ms 0 - 37 MB NPU WideResNet50.tflite
WideResNet50 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 4.09 ms 0 - 10 MB NPU Use Export Script
WideResNet50 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 2.254 ms 0 - 101 MB NPU WideResNet50.tflite
WideResNet50 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 2.65 ms 0 - 104 MB NPU Use Export Script
WideResNet50 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.751 ms 0 - 339 MB NPU WideResNet50.tflite
WideResNet50 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 1.882 ms 0 - 2 MB NPU Use Export Script
WideResNet50 w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.891 ms 0 - 38 MB NPU WideResNet50.tflite
WideResNet50 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 7.791 ms 0 - 91 MB NPU WideResNet50.tflite
WideResNet50 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 9.763 ms 0 - 13 MB NPU Use Export Script
WideResNet50 w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 24.072 ms 0 - 2 MB NPU WideResNet50.tflite
WideResNet50 w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 3.847 ms 0 - 37 MB NPU WideResNet50.tflite
WideResNet50 w8a8 SA7255P ADP Qualcomm® SA7255P QNN 4.09 ms 0 - 10 MB NPU Use Export Script
WideResNet50 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.746 ms 0 - 337 MB NPU WideResNet50.tflite
WideResNet50 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 1.886 ms 0 - 3 MB NPU Use Export Script
WideResNet50 w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.646 ms 0 - 39 MB NPU WideResNet50.tflite
WideResNet50 w8a8 SA8295P ADP Qualcomm® SA8295P QNN 2.804 ms 0 - 16 MB NPU Use Export Script
WideResNet50 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.752 ms 0 - 342 MB NPU WideResNet50.tflite
WideResNet50 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 1.885 ms 0 - 2 MB NPU Use Export Script
WideResNet50 w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 1.891 ms 0 - 38 MB NPU WideResNet50.tflite
WideResNet50 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 1.75 ms 0 - 343 MB NPU WideResNet50.tflite
WideResNet50 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 1.963 ms 0 - 334 MB NPU Use Export Script
WideResNet50 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 15.574 ms 0 - 141 MB NPU WideResNet50.onnx
WideResNet50 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.337 ms 0 - 104 MB NPU WideResNet50.tflite
WideResNet50 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 1.434 ms 0 - 101 MB NPU Use Export Script
WideResNet50 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 13.873 ms 2 - 510 MB NPU WideResNet50.onnx
WideResNet50 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 1.215 ms 1 - 38 MB NPU WideResNet50.tflite
WideResNet50 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 1.266 ms 0 - 43 MB NPU Use Export Script
WideResNet50 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 11.622 ms 2 - 437 MB NPU WideResNet50.onnx
WideResNet50 w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.826 ms 0 - 0 MB NPU Use Export Script
WideResNet50 w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 17.759 ms 79 - 79 MB NPU WideResNet50.onnx

Installation

Install the package via pip:

pip install qai-hub-models

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.wideresnet50.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.wideresnet50.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.wideresnet50.export
Profiling Results
------------------------------------------------------------
WideResNet50
Device                          : cs_8275 (ANDROID 14)                
Runtime                         : TFLITE                              
Estimated inference time (ms)   : 24.4                                
Estimated peak memory usage (MB): [0, 83]                             
Total # Ops                     : 79                                  
Compute Unit(s)                 : npu (79 ops) gpu (0 ops) cpu (0 ops)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.wideresnet50 import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)
        

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.wideresnet50.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.wideresnet50.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 WideResNet50's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of WideResNet50 can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
146
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support