Hugging Face's logo

qualcomm
/
MobileSam

Image Segmentation
PyTorch
LiteRT
foundation
android
Model card Files
xet
Community

MobileSam: Optimized for Mobile Deployment

Faster Segment Anything: Towards lightweight SAM for mobile applications

Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.

This model is an implementation of MobileSam found here.

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

Model Details

  • Model Type: Model_use_case.semantic_segmentation
  • Model Stats:
    • Model checkpoint: vit_t
    • Input resolution: 720p (720x1280)
    • Number of parameters (SAMEncoder): 6.95M
    • Model size (SAMEncoder) (float): 26.6 MB
    • Number of parameters (SAMDecoder): 6.16M
    • Model size (SAMDecoder) (float): 23.7 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
MobileSAMEncoder float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 323.32 ms 4 - 536 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 519.019 ms 0 - 1845 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 460.861 ms 12 - 776 MB NPU MobileSam.dlc
MobileSAMEncoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 194.834 ms 4 - 82 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 151.163 ms 12 - 105 MB NPU MobileSam.dlc
MobileSAMEncoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 343.314 ms 118 - 143 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 198.285 ms 4 - 534 MB NPU MobileSam.tflite
MobileSAMEncoder float SA7255P ADP Qualcomm® SA7255P TFLITE 323.32 ms 4 - 536 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 151.446 ms 15 - 107 MB NPU MobileSam.dlc
MobileSAMEncoder float SA8295P ADP Qualcomm® SA8295P TFLITE 557.47 ms 4 - 1121 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8295P ADP Qualcomm® SA8295P QNN_DLC 453.8 ms 2 - 594 MB NPU MobileSam.dlc
MobileSAMEncoder float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 153.239 ms 12 - 102 MB NPU MobileSam.dlc
MobileSAMEncoder float SA8775P ADP Qualcomm® SA8775P TFLITE 198.285 ms 4 - 534 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 139.876 ms 0 - 523 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 106.741 ms 12 - 1653 MB NPU MobileSam.dlc
MobileSAMEncoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 254.414 ms 126 - 255 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 107.657 ms 3 - 529 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 81.528 ms 0 - 1016 MB NPU MobileSam.dlc
MobileSAMEncoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 186.033 ms 116 - 460 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 98.649 ms 0 - 521 MB NPU MobileSam.tflite
MobileSAMEncoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 72.868 ms 12 - 1073 MB NPU MobileSam.dlc
MobileSAMEncoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 88.506 ms 101 - 465 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 148.428 ms 490 - 490 MB NPU MobileSam.dlc
MobileSAMEncoder float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 359.459 ms 132 - 132 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 14.239 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 8.071 ms 0 - 56 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 8.692 ms 4 - 59 MB NPU MobileSam.dlc
MobileSAMDecoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 6.0 ms 0 - 33 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 4.716 ms 4 - 21 MB NPU MobileSam.dlc
MobileSAMDecoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 8.424 ms 0 - 48 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 7.148 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float SA7255P ADP Qualcomm® SA7255P TFLITE 14.239 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 4.732 ms 4 - 21 MB NPU MobileSam.dlc
MobileSAMDecoder float SA8295P ADP Qualcomm® SA8295P TFLITE 9.377 ms 0 - 51 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8295P ADP Qualcomm® SA8295P QNN_DLC 7.249 ms 2 - 80 MB NPU MobileSam.dlc
MobileSAMDecoder float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 4.736 ms 4 - 21 MB NPU MobileSam.dlc
MobileSAMDecoder float SA8775P ADP Qualcomm® SA8775P TFLITE 7.148 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 4.197 ms 0 - 58 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 3.29 ms 4 - 74 MB NPU MobileSam.dlc
MobileSAMDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.741 ms 3 - 85 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 3.409 ms 0 - 51 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.653 ms 0 - 58 MB NPU MobileSam.dlc
MobileSAMDecoder float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 4.232 ms 3 - 77 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 3.342 ms 0 - 49 MB NPU MobileSam.tflite
MobileSAMDecoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 2.166 ms 4 - 53 MB NPU MobileSam.dlc
MobileSAMDecoder float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 3.513 ms 4 - 85 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 5.165 ms 20 - 20 MB NPU MobileSam.dlc
MobileSAMDecoder float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 8.735 ms 11 - 11 MB NPU MobileSam.onnx.zip

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[mobilesam]" git+https://github.com/ChaoningZhang/MobileSAM@34bbbfd --use-pep517

Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub Workbench 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.mobilesam.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.mobilesam.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.mobilesam.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.mobilesam 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 Workbench. 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.mobilesam.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.mobilesam.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 MobileSam's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
201
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support