Hugging Face's logo

qualcomm
/
PSPNet

Image Segmentation
PyTorch
LiteRT
android
Model card Files
xet
Community

PSPNet: Optimized for Mobile Deployment

Deep learning model for pixel-level semantic segmentation using pyramid pooling

PSPNet (Pyramid Scene Parsing Network) is a semantic segmentation model that captures global context information by applying pyramid pooling modules. It is designed to improve scene understanding by aggregating contextual features at multiple scales.

This repository provides scripts to run PSPNet 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: pspnet101_ade20k.pth
    • Input resolution: 1x3x473x473
    • Number of parameters: 65.7M
    • Model size (float): 251 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
PSPNet float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3725.883 ms 114 - 621 MB NPU PSPNet.tflite
PSPNet float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 1502.055 ms 0 - 465 MB NPU PSPNet.dlc
PSPNet float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 2139.674 ms 10 - 273 MB NPU PSPNet.tflite
PSPNet float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1124.616 ms 0 - 152 MB NPU PSPNet.dlc
PSPNet float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1724.95 ms 0 - 48 MB NPU PSPNet.tflite
PSPNet float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 599.215 ms 3 - 38 MB NPU PSPNet.dlc
PSPNet float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 1308.365 ms 0 - 345 MB NPU PSPNet.onnx.zip
PSPNet float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1814.63 ms 127 - 636 MB NPU PSPNet.tflite
PSPNet float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 647.279 ms 0 - 463 MB NPU PSPNet.dlc
PSPNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1277.954 ms 0 - 689 MB NPU PSPNet.tflite
PSPNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 476.866 ms 3 - 528 MB NPU PSPNet.dlc
PSPNet float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 1003.333 ms 32 - 418 MB NPU PSPNet.onnx.zip
PSPNet float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 1251.199 ms 0 - 507 MB NPU PSPNet.tflite
PSPNet float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 376.561 ms 0 - 456 MB NPU PSPNet.dlc
PSPNet float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 974.643 ms 8 - 391 MB NPU PSPNet.onnx.zip
PSPNet float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1311.447 ms 0 - 520 MB NPU PSPNet.tflite
PSPNet float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 380.886 ms 3 - 471 MB NPU PSPNet.dlc
PSPNet float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1045.72 ms 10 - 404 MB NPU PSPNet.onnx.zip
PSPNet float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 600.96 ms 85 - 85 MB NPU PSPNet.dlc
PSPNet float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 1032.499 ms 265 - 265 MB NPU PSPNet.onnx.zip

Installation

Install the package via pip:

pip install qai-hub-models

Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub Workbench 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.pspnet.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.pspnet.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.pspnet.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.pspnet 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 Workbench. 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.pspnet.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.pspnet.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 PSPNet's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

Community

Downloads last month
10
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support