Hugging Face's logo

qualcomm
/
FastSam-X

Image Segmentation
PyTorch
LiteRT
ONNX
android
Model card Files Community
FastSam-X / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
f77b4ee verified
preview code
|
raw
history blame contribute delete
12 kB
metadata
library_name: pytorch
license: agpl-3.0
tags:
  - android
pipeline_tag: image-segmentation

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: Semantic segmentation
  • Model Stats:
    • Model checkpoint: fastsam-x.pt
    • Inference latency: RealTime
    • Input resolution: 640x640
    • Number of parameters: 72.2M
    • Model size: 276 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
FastSam-X Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 42.606 ms 4 - 61 MB FP16 NPU FastSam-X.tflite
FastSam-X Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 42.402 ms 5 - 8 MB FP16 NPU FastSam-X.so
FastSam-X Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 49.202 ms 11 - 309 MB FP16 NPU FastSam-X.onnx
FastSam-X Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 34.723 ms 3 - 187 MB FP16 NPU FastSam-X.tflite
FastSam-X Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 32.178 ms 5 - 24 MB FP16 NPU FastSam-X.so
FastSam-X Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 36.472 ms 16 - 77 MB FP16 NPU FastSam-X.onnx
FastSam-X Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 30.981 ms 3 - 98 MB FP16 NPU FastSam-X.tflite
FastSam-X Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 27.855 ms 5 - 61 MB FP16 NPU Use Export Script
FastSam-X Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 33.102 ms 11 - 64 MB FP16 NPU FastSam-X.onnx
FastSam-X SA7255P ADP SA7255P TFLITE 2097.231 ms 0 - 94 MB FP16 NPU FastSam-X.tflite
FastSam-X SA7255P ADP SA7255P QNN 2093.89 ms 5 - 12 MB FP16 NPU Use Export Script
FastSam-X SA8255 (Proxy) SA8255P Proxy TFLITE 45.252 ms 4 - 57 MB FP16 NPU FastSam-X.tflite
FastSam-X SA8255 (Proxy) SA8255P Proxy QNN 42.801 ms 5 - 8 MB FP16 NPU Use Export Script
FastSam-X SA8295P ADP SA8295P TFLITE 89.751 ms 4 - 95 MB FP16 NPU FastSam-X.tflite
FastSam-X SA8295P ADP SA8295P QNN 80.148 ms 0 - 14 MB FP16 NPU Use Export Script
FastSam-X SA8650 (Proxy) SA8650P Proxy TFLITE 42.593 ms 4 - 60 MB FP16 NPU FastSam-X.tflite
FastSam-X SA8650 (Proxy) SA8650P Proxy QNN 42.455 ms 5 - 7 MB FP16 NPU Use Export Script
FastSam-X SA8775P ADP SA8775P TFLITE 86.798 ms 4 - 97 MB FP16 NPU FastSam-X.tflite
FastSam-X SA8775P ADP SA8775P QNN 84.171 ms 2 - 12 MB FP16 NPU Use Export Script
FastSam-X QCS8275 (Proxy) QCS8275 Proxy TFLITE 2097.231 ms 0 - 94 MB FP16 NPU FastSam-X.tflite
FastSam-X QCS8275 (Proxy) QCS8275 Proxy QNN 2093.89 ms 5 - 12 MB FP16 NPU Use Export Script
FastSam-X QCS8550 (Proxy) QCS8550 Proxy TFLITE 45.52 ms 4 - 58 MB FP16 NPU FastSam-X.tflite
FastSam-X QCS8550 (Proxy) QCS8550 Proxy QNN 42.282 ms 5 - 7 MB FP16 NPU Use Export Script
FastSam-X QCS9075 (Proxy) QCS9075 Proxy TFLITE 86.798 ms 4 - 97 MB FP16 NPU FastSam-X.tflite
FastSam-X QCS9075 (Proxy) QCS9075 Proxy QNN 84.171 ms 2 - 12 MB FP16 NPU Use Export Script
FastSam-X QCS8450 (Proxy) QCS8450 Proxy TFLITE 86.958 ms 2 - 191 MB FP16 NPU FastSam-X.tflite
FastSam-X QCS8450 (Proxy) QCS8450 Proxy QNN 85.26 ms 5 - 63 MB FP16 NPU Use Export Script
FastSam-X Snapdragon X Elite CRD Snapdragon® X Elite QNN 43.55 ms 5 - 5 MB FP16 NPU Use Export Script
FastSam-X Snapdragon X Elite CRD Snapdragon® X Elite ONNX 48.696 ms 139 - 139 MB FP16 NPU FastSam-X.onnx

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

Profiling Results
------------------------------------------------------------
FastSam-X
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 42.6                   
Estimated peak memory usage (MB): [4, 61]                
Total # Ops                     : 419                    
Compute Unit(s)                 : NPU (419 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_x 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.fastsam_x.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_x.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-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