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
beef419 verified
preview code
|
raw
history blame contribute delete
8.51 kB
metadata
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
    • Number of output classes: 19
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
FFNet-78S-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 5.703 ms 1 - 14 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 11.485 ms 0 - 23 MB INT8 NPU FFNet-78S-Quantized.onnx
FFNet-78S-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 4.078 ms 1 - 32 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 7.814 ms 7 - 156 MB INT8 NPU FFNet-78S-Quantized.onnx
FFNet-78S-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 4.008 ms 0 - 28 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 6.816 ms 13 - 84 MB INT8 NPU FFNet-78S-Quantized.onnx
FFNet-78S-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 35.719 ms 1 - 36 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized RB5 (Proxy) QCS8250 Proxy TFLITE 215.731 ms 1 - 3 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 5.672 ms 1 - 13 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized SA7255P ADP SA7255P TFLITE 145.368 ms 1 - 28 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized SA8255 (Proxy) SA8255P Proxy TFLITE 5.731 ms 1 - 14 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized SA8295P ADP SA8295P TFLITE 11.233 ms 1 - 27 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized SA8650 (Proxy) SA8650P Proxy TFLITE 5.854 ms 1 - 14 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized SA8775P ADP SA8775P TFLITE 7.642 ms 0 - 28 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 7.139 ms 1 - 37 MB INT8 NPU FFNet-78S-Quantized.tflite
FFNet-78S-Quantized Snapdragon X Elite CRD Snapdragon® X Elite ONNX 11.704 ms 22 - 22 MB INT8 NPU FFNet-78S-Quantized.onnx

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

Profiling Results
------------------------------------------------------------
FFNet-78S-Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 5.7                    
Estimated peak memory usage (MB): [1, 14]                
Total # Ops                     : 156                    
Compute Unit(s)                 : NPU (156 ops)

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