Hugging Face's logo

qualcomm
/
MobileSam

Image Segmentation
PyTorch
LiteRT
foundation
android
Model card Files 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 673.998 ms 0 - 1103 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 514.019 ms 0 - 2092 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 391.236 ms 3 - 90 MB NPU MobileSam.tflite
MobileSAMEncoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 403.861 ms 100 - 152 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 395.117 ms 4 - 1109 MB NPU MobileSam.tflite
MobileSAMEncoder float SA7255P ADP Qualcomm® SA7255P TFLITE 673.998 ms 0 - 1103 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 395.135 ms 3 - 94 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8295P ADP Qualcomm® SA8295P TFLITE 554.71 ms 4 - 1116 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 394.656 ms 4 - 87 MB NPU MobileSam.tflite
MobileSAMEncoder float SA8775P ADP Qualcomm® SA8775P TFLITE 395.117 ms 4 - 1109 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 395.827 ms 4 - 68 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 406.853 ms 100 - 151 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 291.427 ms 0 - 1773 MB NPU MobileSam.tflite
MobileSAMEncoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 313.829 ms 121 - 820 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 270.943 ms 0 - 1064 MB NPU MobileSam.tflite
MobileSAMEncoder float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 266.121 ms 126 - 511 MB NPU MobileSam.onnx.zip
MobileSAMEncoder float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 449.032 ms 132 - 132 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 16.511 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 8.596 ms 0 - 53 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 7.302 ms 0 - 31 MB NPU MobileSam.tflite
MobileSAMDecoder float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 8.28 ms 0 - 49 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 8.502 ms 0 - 48 MB NPU MobileSam.tflite
MobileSAMDecoder float SA7255P ADP Qualcomm® SA7255P TFLITE 16.511 ms 0 - 46 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 7.287 ms 0 - 29 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8295P ADP Qualcomm® SA8295P TFLITE 9.971 ms 0 - 53 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 7.293 ms 0 - 31 MB NPU MobileSam.tflite
MobileSAMDecoder float SA8775P ADP Qualcomm® SA8775P TFLITE 8.502 ms 0 - 48 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 7.293 ms 0 - 31 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 8.371 ms 0 - 48 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 5.15 ms 0 - 59 MB NPU MobileSam.tflite
MobileSAMDecoder float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.503 ms 4 - 105 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 4.103 ms 0 - 52 MB NPU MobileSam.tflite
MobileSAMDecoder float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 4.948 ms 1 - 110 MB NPU MobileSam.onnx.zip
MobileSAMDecoder float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 8.383 ms 11 - 11 MB NPU MobileSam.onnx.zip

Installation

Install the package via pip:

pip install "qai-hub-models[mobilesam]"

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.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 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.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
246
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support