Hugging Face's logo

qualcomm
/
FFNet-78S-Quantized

Image Segmentation
PyTorch
TF Lite
ONNX
quantized
real_time
android
Model card Files Community
FFNet-78S-Quantized / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
350a66a verified
preview code
|
raw
history blame
7.44 kB
metadata
datasets:
  - cityscapes
library_name: pytorch
license: bsd-3-clause
pipeline_tag: image-segmentation
tags:
  - quantized
  - real_time
  - android

FFNet-78S-Quantized: Optimized for Mobile Deployment

Semantic segmentation for automotive street scenes

FFNet-78S-Quantized is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

This model is an implementation of FFNet-78S-Quantized found here. This repository provides scripts to run FFNet-78S-Quantized 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: ffnet78S_dBBB_cityscapes_state_dict_quarts
    • Input resolution: 2048x1024
    • Number of parameters: 27.5M
    • Model size: 26.7 MB
Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 TFLite 8.341 ms 1 - 2 MB INT8 NPU FFNet-78S-Quantized.tflite
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 QNN Model Library 5.952 ms 8 - 26 MB INT8 NPU FFNet-78S-Quantized.so

Installation

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

pip install "qai-hub-models[ffnet_78s_quantized]"

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.ffnet_78s_quantized.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.ffnet_78s_quantized.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.ffnet_78s_quantized.export

Profile Job summary of FFNet-78S-Quantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 7.10 ms
Estimated Peak Memory Range: 6.01-6.01 MB
Compute Units: NPU (146) | Total (146)

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.ffnet_78s_quantized import Model

# Load the model
torch_model = Model.from_pretrained()
torch_model.eval()

# 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.

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 FFNet-78S-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of FFNet-78S-Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community