Hugging Face's logo

qualcomm
/
Sequencer2D

Image Classification
PyTorch
LiteRT
android
Model card Files
xet
Community

Sequencer2D: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

Sequencer2D is a vision transformer model that can classify images from the Imagenet dataset.

This model is an implementation of Sequencer2D found here.

This repository provides scripts to run Sequencer2D 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: sequencer2d_s
    • Input resolution: 224x224
    • Number of parameters: 27.6M
    • Model size (float): 106 MB
    • Model size (w8a8): 69.1 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Sequencer2D float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 41.259 ms 0 - 425 MB NPU Sequencer2D.tflite
Sequencer2D float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 52.131 ms 1 - 636 MB NPU Sequencer2D.dlc
Sequencer2D float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 21.942 ms 0 - 312 MB NPU Sequencer2D.tflite
Sequencer2D float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 27.213 ms 0 - 494 MB NPU Sequencer2D.dlc
Sequencer2D float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 19.243 ms 0 - 55 MB NPU Sequencer2D.tflite
Sequencer2D float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 20.871 ms 0 - 112 MB NPU Sequencer2D.dlc
Sequencer2D float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 46.765 ms 0 - 162 MB NPU Sequencer2D.onnx.zip
Sequencer2D float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 21.197 ms 0 - 421 MB NPU Sequencer2D.tflite
Sequencer2D float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 24.902 ms 1 - 599 MB NPU Sequencer2D.dlc
Sequencer2D float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 13.278 ms 0 - 422 MB NPU Sequencer2D.tflite
Sequencer2D float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 14.504 ms 1 - 1765 MB NPU Sequencer2D.dlc
Sequencer2D float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 33.664 ms 0 - 873 MB NPU Sequencer2D.onnx.zip
Sequencer2D float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 11.468 ms 0 - 418 MB NPU Sequencer2D.tflite
Sequencer2D float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 12.322 ms 1 - 670 MB NPU Sequencer2D.dlc
Sequencer2D float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 23.544 ms 1 - 507 MB NPU Sequencer2D.onnx.zip
Sequencer2D float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 10.897 ms 0 - 433 MB NPU Sequencer2D.tflite
Sequencer2D float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 9.407 ms 1 - 865 MB NPU Sequencer2D.dlc
Sequencer2D float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 18.151 ms 1 - 935 MB NPU Sequencer2D.onnx.zip
Sequencer2D float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 21.388 ms 444 - 444 MB NPU Sequencer2D.dlc
Sequencer2D float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 48.318 ms 65 - 65 MB NPU Sequencer2D.onnx.zip
Sequencer2D w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 38.929 ms 0 - 403 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 20.3 ms 0 - 304 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 20.078 ms 0 - 58 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 22.249 ms 0 - 397 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 262.075 ms 30 - 52 MB CPU Sequencer2D.onnx.zip
Sequencer2D w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 271.373 ms 27 - 37 MB CPU Sequencer2D.onnx.zip
Sequencer2D w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 14.566 ms 0 - 408 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 12.907 ms 0 - 393 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 104.365 ms 104 - 200 MB NPU Sequencer2D.onnx.zip
Sequencer2D w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 13.349 ms 0 - 393 MB NPU Sequencer2D.tflite
Sequencer2D w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 101.588 ms 103 - 197 MB NPU Sequencer2D.onnx.zip
Sequencer2D w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 123.908 ms 132 - 132 MB NPU Sequencer2D.onnx.zip

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[sequencer2d]"

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.sequencer2d.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.sequencer2d.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.sequencer2d.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.sequencer2d 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.sequencer2d.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.sequencer2d.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 Sequencer2D's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of Sequencer2D can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
74
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support