Hugging Face's logo

qualcomm
/
DDRNet23-Slim

Image Segmentation
PyTorch
LiteRT
real_time
android
Model card Files
xet
Community

DDRNet23-Slim: Optimized for Mobile Deployment

Segment images or video by class in real-time on device

DDRNet23Slim is a machine learning model that segments an image into semantic classes, specifically designed for road-based scenes. It is designed for the application of self-driving cars.

This model is an implementation of DDRNet23-Slim found here.

This repository provides scripts to run DDRNet23-Slim 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: DDRNet23s_imagenet.pth
    • Inference latency: RealTime
    • Input resolution: 2048x1024
    • Number of output classes: 19
    • Number of parameters: 6.13M
    • Model size (float): 21.7 MB
    • Model size (w8a8): 6.11 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
DDRNet23-Slim float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 113.097 ms 2 - 49 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 95.058 ms 24 - 81 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 49.383 ms 2 - 61 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 59.265 ms 24 - 87 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 41.853 ms 2 - 29 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 31.336 ms 24 - 44 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 24.99 ms 24 - 73 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 49.952 ms 2 - 49 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 38.58 ms 24 - 81 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float SA7255P ADP Qualcomm® SA7255P TFLITE 113.097 ms 2 - 49 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float SA7255P ADP Qualcomm® SA7255P QNN_DLC 95.058 ms 24 - 81 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 42.039 ms 2 - 18 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 31.149 ms 24 - 43 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float SA8295P ADP Qualcomm® SA8295P TFLITE 56.007 ms 2 - 56 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float SA8295P ADP Qualcomm® SA8295P QNN_DLC 42.386 ms 24 - 83 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 41.99 ms 2 - 27 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 31.303 ms 24 - 46 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float SA8775P ADP Qualcomm® SA8775P TFLITE 49.952 ms 2 - 49 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float SA8775P ADP Qualcomm® SA8775P QNN_DLC 38.58 ms 24 - 81 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 26.938 ms 1 - 58 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 21.099 ms 24 - 83 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 16.139 ms 29 - 85 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 21.408 ms 1 - 55 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 15.161 ms 23 - 92 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 12.707 ms 6 - 68 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 18.326 ms 1 - 53 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 11.147 ms 24 - 102 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 8.843 ms 30 - 127 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 32.151 ms 24 - 24 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 24.341 ms 24 - 24 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 99.178 ms 1 - 37 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 141.177 ms 6 - 61 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 50.345 ms 1 - 49 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 78.714 ms 6 - 73 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 50.347 ms 0 - 20 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 73.655 ms 6 - 28 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 100.537 ms 87 - 131 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 51.268 ms 1 - 37 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 74.35 ms 6 - 61 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 158.413 ms 10 - 58 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 564.929 ms 231 - 246 MB CPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 322.059 ms 21 - 39 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 543.09 ms 222 - 233 MB CPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 99.178 ms 1 - 37 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 141.177 ms 6 - 61 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 50.482 ms 0 - 15 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 73.32 ms 6 - 29 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 58.292 ms 1 - 44 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 82.849 ms 6 - 64 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 50.429 ms 0 - 20 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 73.524 ms 6 - 25 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 51.268 ms 1 - 37 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 74.35 ms 6 - 61 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 38.167 ms 1 - 50 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 55.557 ms 6 - 72 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 77.809 ms 104 - 864 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 37.528 ms 1 - 42 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 40.336 ms 6 - 73 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 55.267 ms 97 - 355 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile TFLITE 66.505 ms 8 - 51 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile ONNX 594.033 ms 215 - 232 MB CPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 23.517 ms 1 - 42 MB NPU DDRNet23-Slim.tflite
DDRNet23-Slim w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 46.979 ms 6 - 83 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 56.909 ms 103 - 362 MB NPU DDRNet23-Slim.onnx.zip
DDRNet23-Slim w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 77.18 ms 0 - 0 MB NPU DDRNet23-Slim.dlc
DDRNet23-Slim w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 102.239 ms 128 - 128 MB NPU DDRNet23-Slim.onnx.zip

Installation

Install the 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.ddrnet23_slim.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.ddrnet23_slim.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.ddrnet23_slim.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.ddrnet23_slim 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.ddrnet23_slim.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.ddrnet23_slim.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 DDRNet23-Slim's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of DDRNet23-Slim can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
287
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support