Hugging Peers

DDRNet23-Slim

☆ Save
by Qualcomm-AI-Hub image-segmentation mit
0 downloads 0 likes on ModelScope updated

Model card

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 11.668 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Snapdragon® X Elite 27.666 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Gen 3 Mobile 19.683 ms 29 - 298 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Gen 1 Mobile 46.211 ms 24 - 296 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-8275 34.437 ms 24 - 51 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.647 ms 24 - 40 MB NPU
DDRNet23-Slim ONNX float Qualcomm® QCS8450 46.211 ms 24 - 296 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-9075 35.036 ms 24 - 51 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ IQ-X7181 27.666 ms 24 - 24 MB NPU
DDRNet23-Slim ONNX float Qualcomm® Dragonwing™ Q-8750 14.884 ms 6 - 193 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Elite Mobile 14.884 ms 6 - 193 MB NPU
DDRNet23-Slim ONNX float Snapdragon® 8 Elite Gen 5 Mobile 11.388 ms 5 - 218 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® X2 Elite 43.858 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® X Elite 56.063 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 39.61 ms 7 - 252 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 55.145 ms 8 - 252 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 152.56 ms 6 - 9 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 49.577 ms 6 - 10 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 53.38 ms 6 - 16 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® QCS8450 55.145 ms 8 - 252 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 52.62 ms 6 - 9 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 56.063 ms 7 - 7 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 194.289 ms 5 - 205 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 53.742 ms 6 - 207 MB NPU
DDRNet23-Slim ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 41.02 ms 2 - 201 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Elite Mobile 41.02 ms 2 - 201 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 43.371 ms 1 - 202 MB NPU
DDRNet23-Slim ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 53.742 ms 6 - 207 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® X2 Elite 11.829 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® X Elite 33.886 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Gen 3 Mobile 22.399 ms 17 - 290 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Gen 1 Mobile 66.58 ms 25 - 301 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 38.336 ms 24 - 53 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 32.796 ms 24 - 27 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8775P 40.464 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8650P 40.464 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8255P 40.464 ms 24 - 222 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® QCS8450 66.58 ms 25 - 301 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 41.359 ms 24 - 52 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 33.886 ms 24 - 24 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® Dragonwing™ Q-8750 15.467 ms 17 - 237 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA7255P 98.441 ms 24 - 221 MB NPU
DDRNet23-Slim QNN_DLC float Qualcomm® SA8295P 43.476 ms 24 - 230 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Elite Mobile 15.467 ms 17 - 237 MB NPU
DDRNet23-Slim QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 10.526 ms 20 - 257 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® X2 Elite 29.67 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® X Elite 58.866 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 42.002 ms 6 - 251 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 80.248 ms 7 - 254 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 54.958 ms 6 - 15 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 56.106 ms 6 - 8 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8775P 56.921 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8650P 56.921 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8255P 56.921 ms 6 - 206 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® QCS8450 80.248 ms 7 - 254 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 57.234 ms 6 - 14 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 58.866 ms 6 - 6 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 39.597 ms 6 - 222 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA7255P 107.866 ms 6 - 205 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Qualcomm® SA8295P 66.523 ms 6 - 207 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 39.597 ms 6 - 222 MB NPU
DDRNet23-Slim QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 28.762 ms 6 - 240 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Gen 3 Mobile 22.488 ms 2 - 283 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Gen 1 Mobile 66.628 ms 2 - 287 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ IQ-8275 38.304 ms 0 - 42 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.183 ms 2 - 6 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8775P 40.407 ms 3 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8650P 40.407 ms 3 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8255P 40.407 ms 3 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® QCS8450 66.628 ms 2 - 287 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ IQ-9075 41.017 ms 0 - 41 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® Dragonwing™ Q-8750 15.674 ms 2 - 229 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA7255P 98.325 ms 3 - 205 MB NPU
DDRNet23-Slim TFLITE float Qualcomm® SA8295P 43.493 ms 2 - 214 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Elite Mobile 15.674 ms 2 - 229 MB NPU
DDRNet23-Slim TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 10.458 ms 2 - 242 MB NPU

License

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

References

Community