Hugging Face's logo

qualcomm
/
DDRNet23-Slim

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community

DDRNet23-Slim: Optimized for Qualcomm Devices

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 is based on the implementation of DDRNet23-Slim found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit DDRNet23-Slim on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for DDRNet23-Slim on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Inference latency: RealTime
  • Input resolution: 2048x1024
  • Model checkpoint: DDRNet23s_imagenet.pth
  • Model size (float): 21.7 MB
  • Model size (w8a8): 6.11 MB
  • Number of output classes: 19
  • Number of parameters: 6.13M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DDRNet23-Slim ONNX float Snapdragon® X2 Elite 11.622 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Snapdragon® X Elite 27.628 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Gen 3 Mobile 20.062 ms 32 - 302 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Gen 1 Mobile 46.217 ms 25 - 297 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-8275 34.693 ms 24 - 51 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.408 ms 24 - 41 MB NPU
DDRNet23-Slim ONNX float Qualcomm® QCS8450 46.217 ms 25 - 297 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-9075 36.157 ms 24 - 51 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-X7181 27.628 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ Q-8750 14.838 ms 8 - 195 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Elite Mobile 14.838 ms 8 - 195 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Elite Gen 5 Mobile 11.426 ms 5 - 221 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® X2 Elite 43.654 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® X Elite 55.941 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 39.701 ms 7 - 251 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 55.128 ms 8 - 253 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 152.821 ms 6 - 9 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 49.825 ms 6 - 10 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 53.307 ms 6 - 9 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® QCS8450 55.128 ms 8 - 253 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 52.53 ms 6 - 9 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 55.941 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 195.364 ms 5 - 205 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 53.97 ms 3 - 204 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 40.928 ms 2 - 200 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Elite Mobile 40.928 ms 2 - 200 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 43.401 ms 2 - 204 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 53.97 ms 3 - 204 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® X2 Elite 11.816 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® X Elite 34.3 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Gen 3 Mobile 22.213 ms 24 - 298 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Gen 1 Mobile 66.756 ms 24 - 300 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 38.171 ms 24 - 53 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 98.423 ms 15 - 212 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 32.861 ms 24 - 248 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8775P 40.493 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8650P 40.493 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8255P 40.493 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® QCS8450 66.756 ms 24 - 300 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 41.374 ms 26 - 54 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 34.3 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ Q-8750 15.645 ms 15 - 235 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA7255P 98.423 ms 15 - 212 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8295P 43.46 ms 24 - 231 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Elite Mobile 15.645 ms 15 - 235 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 10.523 ms 0 - 237 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® X2 Elite 29.275 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® X Elite 58.906 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 41.986 ms 6 - 251 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 80.357 ms 7 - 254 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 107.789 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 56.281 ms 6 - 8 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8775P 56.852 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8650P 56.852 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8255P 56.852 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® QCS8450 80.357 ms 7 - 254 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 57.775 ms 6 - 14 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 58.906 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 39.648 ms 6 - 222 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA7255P 107.789 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8295P 66.549 ms 6 - 208 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 39.648 ms 6 - 222 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 28.775 ms 6 - 240 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Gen 3 Mobile 22.737 ms 1 - 284 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Gen 1 Mobile 66.442 ms 3 - 287 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ IQ-8275 38.339 ms 0 - 41 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ IQ-8275 98.299 ms 0 - 202 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.275 ms 2 - 5 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8775P 40.418 ms 2 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8650P 40.418 ms 2 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8255P 40.418 ms 2 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® QCS8450 66.442 ms 3 - 287 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ IQ-9075 41.552 ms 0 - 41 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ Q-8750 15.589 ms 2 - 226 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA7255P 98.299 ms 0 - 202 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8295P 43.445 ms 2 - 214 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Elite Mobile 15.589 ms 2 - 226 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 10.46 ms 2 - 242 MB NPU

License

  • The license for the original implementation of DDRNet23-Slim can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/DDRNet23-Slim