library_name: pytorch
license: other
tags:
- foundation
- android
pipeline_tag: image-segmentation
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 | 324.864 ms | 0 - 529 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 260.424 ms | 0 - 528 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 514.336 ms | 0 - 1846 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 552.762 ms | 12 - 1872 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 196.222 ms | 4 - 86 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 155.047 ms | 12 - 81 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 339.53 ms | 96 - 161 MB | NPU | MobileSam.onnx.zip |
| MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 198.65 ms | 4 - 533 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 160.433 ms | 3 - 1080 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 324.864 ms | 0 - 529 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 260.424 ms | 0 - 528 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 197.144 ms | 4 - 84 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 156.008 ms | 12 - 83 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 558.486 ms | 1 - 1116 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 196.223 ms | 4 - 88 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 155.286 ms | 9 - 76 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 198.65 ms | 4 - 533 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 160.433 ms | 3 - 1080 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 138.04 ms | 0 - 525 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 111.694 ms | 12 - 536 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 255.0 ms | 127 - 262 MB | NPU | MobileSam.onnx.zip |
| MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 110.676 ms | 4 - 532 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 91.237 ms | 12 - 508 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 185.566 ms | 116 - 457 MB | NPU | MobileSam.onnx.zip |
| MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 93.109 ms | 0 - 521 MB | NPU | MobileSam.tflite |
| MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 73.307 ms | 12 - 1071 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 155.196 ms | 126 - 360 MB | NPU | MobileSam.onnx.zip |
| MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 150.151 ms | 954 - 954 MB | NPU | MobileSam.dlc |
| MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 344.225 ms | 132 - 132 MB | NPU | MobileSam.onnx.zip |
| MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.769 ms | 0 - 48 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.294 ms | 4 - 140 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.45 ms | 0 - 53 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 11.466 ms | 4 - 73 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.301 ms | 0 - 31 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.053 ms | 4 - 26 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.043 ms | 0 - 51 MB | NPU | MobileSam.onnx.zip |
| MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.447 ms | 0 - 51 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.089 ms | 2 - 139 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.769 ms | 0 - 48 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.294 ms | 4 - 140 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 6.303 ms | 0 - 30 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 5.071 ms | 4 - 29 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.828 ms | 0 - 51 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 6.311 ms | 0 - 31 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 5.091 ms | 4 - 33 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.447 ms | 0 - 51 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.089 ms | 2 - 139 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.424 ms | 0 - 55 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.536 ms | 5 - 154 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.48 ms | 4 - 84 MB | NPU | MobileSam.onnx.zip |
| MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.469 ms | 0 - 54 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.635 ms | 4 - 135 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.102 ms | 1 - 74 MB | NPU | MobileSam.onnx.zip |
| MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 3.158 ms | 0 - 50 MB | NPU | MobileSam.tflite |
| MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.334 ms | 4 - 57 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.386 ms | 4 - 84 MB | NPU | MobileSam.onnx.zip |
| MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 5.517 ms | 64 - 64 MB | NPU | MobileSam.dlc |
| MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.453 ms | 11 - 11 MB | NPU | MobileSam.onnx.zip |
Installation
Install the package via pip:
pip install "qai-hub-models[mobilesam]" git+https://github.com/ChaoningZhang/MobileSAM@34bbbfd --use-pep517
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 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.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 (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.soexport ): This sample app provides instructions on how to use the.soshared 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
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.