Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
LiteRT
backbone
bu_auto
android
Model card Files
xet
Community

EfficientNet-V2-s: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

EfficientNetV2-s 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 EfficientNet-V2-s found here.

This repository provides scripts to run EfficientNet-V2-s 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: 384x384
    • Number of parameters: 21.4M
    • Model size (float): 81.7 MB
    • Model size (w8a16): 27.2 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
EfficientNet-V2-s float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 11.004 ms 0 - 77 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 10.814 ms 0 - 34 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 4.865 ms 0 - 90 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 5.542 ms 1 - 44 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 2.724 ms 0 - 364 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 2.565 ms 0 - 15 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 2.646 ms 0 - 109 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 3.867 ms 0 - 78 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 3.709 ms 1 - 35 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.986 ms 0 - 107 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.904 ms 1 - 65 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 1.948 ms 0 - 70 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 1.569 ms 0 - 81 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.491 ms 1 - 41 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 1.588 ms 0 - 42 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.277 ms 0 - 81 MB NPU EfficientNet-V2-s.tflite
EfficientNet-V2-s float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.227 ms 1 - 41 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1.358 ms 1 - 42 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 2.865 ms 217 - 217 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 2.69 ms 47 - 47 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 5.362 ms 0 - 66 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 3.215 ms 0 - 77 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 2.62 ms 0 - 22 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 2.714 ms 0 - 50 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 2.996 ms 0 - 65 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 9.397 ms 0 - 124 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 131.694 ms 24 - 46 MB CPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 128.347 ms 19 - 33 MB CPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.784 ms 0 - 78 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 1.8 ms 0 - 83 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.246 ms 0 - 71 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 1.384 ms 0 - 76 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.021 ms 0 - 71 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1.148 ms 0 - 77 MB NPU EfficientNet-V2-s.onnx.zip
EfficientNet-V2-s w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 2.918 ms 100 - 100 MB NPU EfficientNet-V2-s.dlc
EfficientNet-V2-s w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 2.729 ms 26 - 26 MB NPU EfficientNet-V2-s.onnx.zip

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.efficientnet_v2_s.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.efficientnet_v2_s.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.efficientnet_v2_s.export

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.efficientnet_v2_s import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S25")

# 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.efficientnet_v2_s.demo --eval-mode 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.efficientnet_v2_s.demo -- --eval-mode 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 EfficientNet-V2-s's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of EfficientNet-V2-s can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
270
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support