Hugging Face's logo

qualcomm
/
FFNet-122NS-LowRes

Image Segmentation
PyTorch
LiteRT
android
Model card Files
xet
Community

FFNet-122NS-LowRes: Optimized for Mobile Deployment

Semantic segmentation for automotive street scenes

FFNet-122NS-LowRes 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-122NS-LowRes found here.

This repository provides scripts to run FFNet-122NS-LowRes 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: ffnet122NS_CCC_cityscapes_state_dict_quarts_pre_down
    • Input resolution: 1024x512
    • Number of output classes: 19
    • Number of parameters: 32.1M
    • Model size (float): 123 MB
    • Model size (w8a8): 31.3 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
FFNet-122NS-LowRes float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 40.165 ms 1 - 61 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 37.962 ms 6 - 37 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 15.025 ms 1 - 119 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 23.692 ms 5 - 47 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 12.163 ms 1 - 13 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 11.14 ms 6 - 20 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 7.036 ms 7 - 20 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 15.463 ms 0 - 61 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 14.24 ms 3 - 34 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float SA7255P ADP Qualcomm® SA7255P TFLITE 40.165 ms 1 - 61 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float SA7255P ADP Qualcomm® SA7255P QNN_DLC 37.962 ms 6 - 37 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 12.171 ms 0 - 17 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 11.178 ms 6 - 21 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float SA8295P ADP Qualcomm® SA8295P TFLITE 17.146 ms 1 - 61 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float SA8295P ADP Qualcomm® SA8295P QNN_DLC 16.491 ms 4 - 34 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 12.174 ms 1 - 15 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 11.166 ms 6 - 20 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float SA8775P ADP Qualcomm® SA8775P TFLITE 15.463 ms 0 - 61 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float SA8775P ADP Qualcomm® SA8775P QNN_DLC 14.24 ms 3 - 34 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 8.299 ms 1 - 119 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 7.742 ms 6 - 46 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.016 ms 6 - 62 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 6.814 ms 1 - 66 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 6.655 ms 6 - 43 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 6.619 ms 1 - 43 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 5.968 ms 0 - 64 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 5.685 ms 6 - 44 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 3.713 ms 4 - 47 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 11.736 ms 94 - 94 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 7.173 ms 57 - 57 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 6.458 ms 0 - 60 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 9.28 ms 2 - 65 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 3.186 ms 0 - 103 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 6.824 ms 2 - 100 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 2.84 ms 0 - 196 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 4.479 ms 2 - 183 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 2.98 ms 0 - 140 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 3.323 ms 0 - 60 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 4.958 ms 2 - 64 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 110.454 ms 7 - 41 MB GPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 20.195 ms 2 - 74 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 78.966 ms 58 - 81 MB CPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 68.636 ms 12 - 24 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 70.953 ms 58 - 73 MB CPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 6.458 ms 0 - 60 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 9.28 ms 2 - 65 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 2.849 ms 0 - 193 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 4.474 ms 0 - 183 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 4.142 ms 0 - 65 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 6.009 ms 2 - 69 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 2.841 ms 0 - 11 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 4.476 ms 1 - 182 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 3.323 ms 0 - 60 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 4.958 ms 2 - 64 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 2.053 ms 0 - 104 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 3.172 ms 2 - 98 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 2.121 ms 0 - 107 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 1.662 ms 0 - 67 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.192 ms 2 - 71 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 1.784 ms 0 - 72 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile TFLITE 4.275 ms 0 - 68 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_DLC 5.895 ms 2 - 71 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile ONNX 84.438 ms 59 - 80 MB CPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.57 ms 0 - 64 MB NPU FFNet-122NS-LowRes.tflite
FFNet-122NS-LowRes w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.801 ms 2 - 67 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1.607 ms 1 - 71 MB NPU FFNet-122NS-LowRes.onnx.zip
FFNet-122NS-LowRes w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.81 ms 171 - 171 MB NPU FFNet-122NS-LowRes.dlc
FFNet-122NS-LowRes w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 2.94 ms 30 - 30 MB NPU FFNet-122NS-LowRes.onnx.zip

Installation

Install the package via pip:

pip install "qai-hub-models[ffnet-122ns-lowres]"

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_122ns_lowres.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_122ns_lowres.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_122ns_lowres.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.ffnet_122ns_lowres 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.ffnet_122ns_lowres.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.ffnet_122ns_lowres.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 FFNet-122NS-LowRes's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of FFNet-122NS-LowRes can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
378
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support