Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
LiteRT
android
Model card Files
xet
Community

ConvNext-Base: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

ConvNextBase 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-Base found here.

This repository provides scripts to run ConvNext-Base 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: 88.6M
    • Model size (float): 338 MB
    • Model size (w8a16): 88.7 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
ConvNext-Base float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 41.59 ms 0 - 231 MB NPU ConvNext-Base.tflite
ConvNext-Base float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 42.288 ms 1 - 236 MB NPU ConvNext-Base.dlc
ConvNext-Base float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 18.272 ms 0 - 247 MB NPU ConvNext-Base.tflite
ConvNext-Base float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 20.554 ms 1 - 248 MB NPU ConvNext-Base.dlc
ConvNext-Base float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 7.377 ms 0 - 23 MB NPU ConvNext-Base.tflite
ConvNext-Base float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 8.121 ms 1 - 24 MB NPU ConvNext-Base.dlc
ConvNext-Base float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 7.438 ms 0 - 24 MB NPU ConvNext-Base.onnx.zip
ConvNext-Base float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 11.363 ms 0 - 231 MB NPU ConvNext-Base.tflite
ConvNext-Base float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 11.975 ms 1 - 236 MB NPU ConvNext-Base.dlc
ConvNext-Base float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 7.313 ms 0 - 25 MB NPU ConvNext-Base.tflite
ConvNext-Base float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 8.153 ms 1 - 24 MB NPU ConvNext-Base.dlc
ConvNext-Base float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 7.449 ms 0 - 23 MB NPU ConvNext-Base.onnx.zip
ConvNext-Base float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 5.563 ms 0 - 244 MB NPU ConvNext-Base.tflite
ConvNext-Base float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 6.009 ms 1 - 244 MB NPU ConvNext-Base.dlc
ConvNext-Base float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.483 ms 1 - 242 MB NPU ConvNext-Base.onnx.zip
ConvNext-Base float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 4.809 ms 0 - 235 MB NPU ConvNext-Base.tflite
ConvNext-Base float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 5.34 ms 1 - 239 MB NPU ConvNext-Base.dlc
ConvNext-Base float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 5.044 ms 0 - 234 MB NPU ConvNext-Base.onnx.zip
ConvNext-Base float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 8.501 ms 1229 - 1229 MB NPU ConvNext-Base.dlc
ConvNext-Base float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 7.461 ms 176 - 176 MB NPU ConvNext-Base.onnx.zip
ConvNext-Base w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 14.365 ms 0 - 128 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 9.039 ms 0 - 139 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 5.843 ms 0 - 32 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 6.108 ms 0 - 127 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 33.238 ms 0 - 219 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 5.862 ms 0 - 32 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 4.139 ms 0 - 140 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 3.752 ms 0 - 130 MB NPU ConvNext-Base.dlc
ConvNext-Base w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 6.232 ms 454 - 454 MB NPU ConvNext-Base.dlc

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.convnext_base.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_base.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_base.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.convnext_base 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.convnext_base.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.convnext_base.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 ConvNext-Base's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
66
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support