Edit model card

Unet-Segmentation: Optimized for Mobile Deployment

Real-time segmentation optimized for mobile and edge

UNet is a machine learning model that produces a segmentation mask for an image. The most basic use case will label each pixel in the image as being in the foreground or the background. More advanced usage will assign a class label to each pixel. This version of the model was trained on the data from Kaggle's Carvana Image Masking Challenge (see https://www.kaggle.com/c/carvana-image-masking-challenge) and is used for vehicle segmentation.

This model is an implementation of Unet-Segmentation found here.

This repository provides scripts to run Unet-Segmentation 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: unet_carvana_scale1.0_epoch2
    • Input resolution: 224x224
    • Number of parameters: 31.0M
    • Model size: 118 MB
    • Number of output classes: 2 (foreground / background)
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
Unet-Segmentation Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 151.145 ms 6 - 442 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 144.285 ms 9 - 27 MB FP16 NPU Unet-Segmentation.so
Unet-Segmentation Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 160.989 ms 16 - 19 MB FP16 NPU Unet-Segmentation.onnx
Unet-Segmentation Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 111.618 ms 5 - 390 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 111.94 ms 9 - 98 MB FP16 NPU Unet-Segmentation.so
Unet-Segmentation Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 112.373 ms 1 - 402 MB FP16 NPU Unet-Segmentation.onnx
Unet-Segmentation Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 102.555 ms 6 - 119 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 102.226 ms 9 - 110 MB FP16 NPU Use Export Script
Unet-Segmentation Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 105.106 ms 16 - 133 MB FP16 NPU Unet-Segmentation.onnx
Unet-Segmentation QCS8550 (Proxy) QCS8550 Proxy TFLITE 148.091 ms 6 - 731 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation QCS8550 (Proxy) QCS8550 Proxy QNN 142.493 ms 10 - 11 MB FP16 NPU Use Export Script
Unet-Segmentation SA8255 (Proxy) SA8255P Proxy TFLITE 154.964 ms 6 - 217 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation SA8255 (Proxy) SA8255P Proxy QNN 139.68 ms 12 - 13 MB FP16 NPU Use Export Script
Unet-Segmentation SA8775 (Proxy) SA8775P Proxy TFLITE 152.816 ms 6 - 442 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation SA8775 (Proxy) SA8775P Proxy QNN 138.994 ms 10 - 12 MB FP16 NPU Use Export Script
Unet-Segmentation SA8650 (Proxy) SA8650P Proxy TFLITE 148.639 ms 6 - 442 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation SA8650 (Proxy) SA8650P Proxy QNN 140.975 ms 10 - 11 MB FP16 NPU Use Export Script
Unet-Segmentation SA8295P ADP SA8295P TFLITE 274.979 ms 7 - 120 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation SA8295P ADP SA8295P QNN 266.023 ms 0 - 6 MB FP16 NPU Use Export Script
Unet-Segmentation QCS8450 (Proxy) QCS8450 Proxy TFLITE 316.171 ms 5 - 390 MB FP16 NPU Unet-Segmentation.tflite
Unet-Segmentation QCS8450 (Proxy) QCS8450 Proxy QNN 280.84 ms 5 - 93 MB FP16 NPU Use Export Script
Unet-Segmentation Snapdragon X Elite CRD Snapdragon® X Elite QNN 135.873 ms 9 - 9 MB FP16 NPU Use Export Script
Unet-Segmentation Snapdragon X Elite CRD Snapdragon® X Elite ONNX 146.944 ms 54 - 54 MB FP16 NPU Unet-Segmentation.onnx

Installation

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

pip install qai-hub-models

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.unet_segmentation.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.unet_segmentation.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.unet_segmentation.export
Profiling Results
------------------------------------------------------------
Unet-Segmentation
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 151.1                  
Estimated peak memory usage (MB): [6, 442]               
Total # Ops                     : 32                     
Compute Unit(s)                 : NPU (32 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.unet_segmentation import 

# Load the model

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

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.unet_segmentation.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.unet_segmentation.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 Unet-Segmentation's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Inference API (serverless) does not yet support pytorch models for this pipeline type.