FastSam-S: Optimized for Mobile Deployment

Generate high quality segmentation mask on device

The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.

This model is an implementation of FastSam-S found here.

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

Model Details

Model Type: Semantic segmentation
Model Stats:
- Model checkpoint: fastsam-s.pt
- Inference latency: RealTime
- Input resolution: 640x640
- Number of parameters: 11.8M
- Model size: 45.1 MB

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
FastSam-S	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	8.104 ms	5 - 22 MB	FP16	NPU	FastSam-S.so
FastSam-S	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	9.535 ms	3 - 24 MB	FP16	NPU	FastSam-S.onnx
FastSam-S	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	5.994 ms	67 - 104 MB	FP16	NPU	FastSam-S.so
FastSam-S	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	6.6 ms	15 - 97 MB	FP16	NPU	FastSam-S.onnx
FastSam-S	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	5.49 ms	5 - 35 MB	FP16	NPU	Use Export Script
FastSam-S	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	5.363 ms	16 - 64 MB	FP16	NPU	FastSam-S.onnx
FastSam-S	QCS8550 (Proxy)	QCS8550 Proxy	QNN	7.622 ms	5 - 6 MB	FP16	NPU	Use Export Script
FastSam-S	SA7255P ADP	SA7255P	QNN	257.585 ms	5 - 10 MB	FP16	NPU	Use Export Script
FastSam-S	SA8255 (Proxy)	SA8255P Proxy	QNN	7.649 ms	5 - 10 MB	FP16	NPU	Use Export Script
FastSam-S	SA8295P ADP	SA8295P	QNN	13.964 ms	0 - 6 MB	FP16	NPU	Use Export Script
FastSam-S	SA8650 (Proxy)	SA8650P Proxy	QNN	7.68 ms	5 - 6 MB	FP16	NPU	Use Export Script
FastSam-S	SA8775P ADP	SA8775P	QNN	14.14 ms	2 - 7 MB	FP16	NPU	Use Export Script
FastSam-S	QCS8450 (Proxy)	QCS8450 Proxy	QNN	14.048 ms	5 - 38 MB	FP16	NPU	Use Export Script
FastSam-S	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	9.897 ms	20 - 20 MB	FP16	NPU	FastSam-S.onnx

Installation

This model can be installed as a Python package via pip.

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

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.fastsam_s.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.fastsam_s.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.fastsam_s.export

Profiling Results
------------------------------------------------------------
FastSam-S
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 8.1                    
Estimated peak memory usage (MB): [5, 22]                
Total # Ops                     : 286                    
Compute Unit(s)                 : NPU (286 ops)

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.fastsam_s import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S23")

# 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.fastsam_s.demo --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.fastsam_s.demo -- --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 FastSam-S's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

The license for the original implementation of FastSam-S 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.