Hugging Face's logo

qualcomm
/
FastSam-X

Image Segmentation
PyTorch
LiteRT
android
Model card Files
xet
Community

FastSam-X: 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-X found here.

This repository provides scripts to run FastSam-X 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: fastsam-x.pt
    • Inference latency: RealTime
    • Input resolution: 640x640
    • Number of parameters: 72.2M
    • Model size (float): 276 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
FastSam-X float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 280.689 ms 4 - 122 MB NPU FastSam-X.tflite
FastSam-X float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 277.39 ms 5 - 101 MB NPU FastSam-X.dlc
FastSam-X float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 86.362 ms 4 - 198 MB NPU FastSam-X.tflite
FastSam-X float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 88.834 ms 5 - 96 MB NPU FastSam-X.dlc
FastSam-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 45.165 ms 4 - 64 MB NPU FastSam-X.tflite
FastSam-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 42.444 ms 5 - 36 MB NPU FastSam-X.dlc
FastSam-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 49.774 ms 0 - 185 MB NPU FastSam-X.onnx.zip
FastSam-X float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 70.508 ms 4 - 122 MB NPU FastSam-X.tflite
FastSam-X float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 68.194 ms 4 - 97 MB NPU FastSam-X.dlc
FastSam-X float SA7255P ADP Qualcomm® SA7255P TFLITE 280.689 ms 4 - 122 MB NPU FastSam-X.tflite
FastSam-X float SA7255P ADP Qualcomm® SA7255P QNN_DLC 277.39 ms 5 - 101 MB NPU FastSam-X.dlc
FastSam-X float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 45.416 ms 1 - 59 MB NPU FastSam-X.tflite
FastSam-X float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 43.314 ms 5 - 37 MB NPU FastSam-X.dlc
FastSam-X float SA8295P ADP Qualcomm® SA8295P TFLITE 89.467 ms 4 - 103 MB NPU FastSam-X.tflite
FastSam-X float SA8295P ADP Qualcomm® SA8295P QNN_DLC 75.254 ms 5 - 85 MB NPU FastSam-X.dlc
FastSam-X float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 45.16 ms 4 - 64 MB NPU FastSam-X.tflite
FastSam-X float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 43.343 ms 7 - 34 MB NPU FastSam-X.dlc
FastSam-X float SA8775P ADP Qualcomm® SA8775P TFLITE 70.508 ms 4 - 122 MB NPU FastSam-X.tflite
FastSam-X float SA8775P ADP Qualcomm® SA8775P QNN_DLC 68.194 ms 4 - 97 MB NPU FastSam-X.dlc
FastSam-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 34.22 ms 2 - 207 MB NPU FastSam-X.tflite
FastSam-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 34.759 ms 5 - 118 MB NPU FastSam-X.dlc
FastSam-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 36.367 ms 15 - 117 MB NPU FastSam-X.onnx.zip
FastSam-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 26.527 ms 3 - 124 MB NPU FastSam-X.tflite
FastSam-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 26.581 ms 5 - 122 MB NPU FastSam-X.dlc
FastSam-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 27.619 ms 10 - 118 MB NPU FastSam-X.onnx.zip
FastSam-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 21.287 ms 4 - 120 MB NPU FastSam-X.tflite
FastSam-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 18.497 ms 5 - 122 MB NPU FastSam-X.dlc
FastSam-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 20.826 ms 15 - 141 MB NPU FastSam-X.onnx.zip
FastSam-X float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 45.097 ms 349 - 349 MB NPU FastSam-X.dlc
FastSam-X float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 46.916 ms 140 - 140 MB NPU FastSam-X.onnx.zip

Installation

Install the package via pip:

pip install "qai-hub-models[fastsam-x]"

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_x.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_x.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_x.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.fastsam_x 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.fastsam_x.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.fastsam_x.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 FastSam-X's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
88
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support