Hugging Face's logo

qualcomm
/
DeepLabV3-Plus-MobileNet

Image Segmentation
PyTorch
android
Model card Files
xet
 Community

DeepLabV3-Plus-MobileNet: Optimized for Qualcomm Devices

DeepLabV3 is designed for semantic segmentation at multiple scales, trained on the various datasets. It uses MobileNet as a backbone.

This is based on the implementation of DeepLabV3-Plus-MobileNet 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 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit DeepLabV3-Plus-MobileNet 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 DeepLabV3-Plus-MobileNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 513x513
  • Model checkpoint: VOC2012
  • Model size (float): 22.2 MB
  • Model size (w8a16): 6.67 MB
  • Number of output classes: 21
  • Number of parameters: 5.80M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 4.204 ms 2 - 170 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 6.114 ms 2 - 166 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® X2 Elite 4.794 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® X Elite 11.378 ms 10 - 10 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Gen 3 Mobile 7.228 ms 4 - 199 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Gen 1 Mobile 17.037 ms 4 - 198 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® Dragonwing™ IQ-8275 17.574 ms 3 - 7 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 11.007 ms 0 - 12 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® QCS8450 17.037 ms 4 - 198 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® Dragonwing™ IQ-9075 16.783 ms 3 - 6 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 11.378 ms 10 - 10 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® Dragonwing™ Q-8750 6.114 ms 2 - 166 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.915 ms 0 - 181 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.02 ms 2 - 179 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® X2 Elite 3.494 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® X Elite 7.391 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 5.177 ms 2 - 212 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 9.124 ms 2 - 213 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 31.902 ms 2 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 7.654 ms 2 - 6 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.085 ms 0 - 105 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® QCS8450 9.124 ms 2 - 213 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 7.347 ms 2 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.391 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 100.395 ms 4 - 234 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 12.199 ms 2 - 179 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 4.02 ms 2 - 179 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 12.199 ms 2 - 179 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.404 ms 0 - 172 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.877 ms 0 - 171 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® X2 Elite 1.643 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® X Elite 3.647 ms 6 - 6 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 2.371 ms 0 - 199 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 4.79 ms 1 - 200 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 13.949 ms 1 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 3.58 ms 0 - 4 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.486 ms 0 - 76 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® QCS8450 4.79 ms 1 - 200 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 3.698 ms 1 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 3.647 ms 6 - 6 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 47.501 ms 0 - 184 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 5.327 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 1.877 ms 0 - 171 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 5.327 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 4.359 ms 3 - 178 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 6.254 ms 0 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® X2 Elite 5.492 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® X Elite 12.324 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 8.083 ms 3 - 201 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 18.232 ms 2 - 198 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 18.805 ms 3 - 9 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 11.526 ms 3 - 5 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8775P 17.501 ms 0 - 163 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8650P 17.501 ms 0 - 163 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8255P 17.501 ms 0 - 163 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® QCS8450 18.232 ms 2 - 198 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 17.854 ms 3 - 9 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 12.324 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 6.254 ms 0 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8295P 20.144 ms 0 - 159 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.228 ms 2 - 175 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.563 ms 2 - 172 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® X2 Elite 4.405 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® X Elite 9.258 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 6.172 ms 2 - 210 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 10.484 ms 2 - 211 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 35.429 ms 3 - 7 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 8.816 ms 2 - 6 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.576 ms 2 - 77 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8775P 9.077 ms 2 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8650P 9.077 ms 2 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8255P 9.077 ms 2 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCS8450 10.484 ms 2 - 211 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 8.812 ms 2 - 5 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 9.258 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 113.355 ms 2 - 220 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 13.942 ms 2 - 178 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 4.563 ms 2 - 172 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA7255P 21.857 ms 2 - 176 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8295P 12.565 ms 2 - 179 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 13.942 ms 2 - 178 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.556 ms 1 - 168 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.09 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® X2 Elite 2.101 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® X Elite 4.562 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 2.869 ms 1 - 185 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 6.565 ms 1 - 191 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 15.238 ms 1 - 4 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 4.175 ms 0 - 4 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.107 ms 1 - 39 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8775P 4.663 ms 1 - 166 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8650P 4.663 ms 1 - 166 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8255P 4.663 ms 1 - 166 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCS8450 6.565 ms 1 - 191 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 4.443 ms 1 - 4 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 4.562 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 46.32 ms 1 - 180 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 6.373 ms 1 - 165 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 2.09 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA7255P 10.611 ms 1 - 163 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8295P 6.129 ms 1 - 162 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.373 ms 1 - 165 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 4.36 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 6.267 ms 0 - 168 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Gen 3 Mobile 8.068 ms 0 - 207 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Gen 1 Mobile 18.204 ms 0 - 203 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 18.831 ms 0 - 19 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 11.451 ms 0 - 2 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8775P 17.561 ms 0 - 165 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8650P 17.561 ms 0 - 165 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8255P 17.561 ms 0 - 165 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® QCS8450 18.204 ms 0 - 203 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 18.078 ms 0 - 19 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® Dragonwing™ Q-8750 6.267 ms 0 - 168 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA7255P 58.82 ms 0 - 163 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8295P 20.157 ms 0 - 160 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.638 ms 0 - 173 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.15 ms 0 - 174 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 2.753 ms 0 - 193 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 5.903 ms 0 - 197 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 16.807 ms 0 - 12 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 4.194 ms 0 - 11 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.999 ms 0 - 2 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8775P 4.5 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8650P 4.5 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8255P 4.5 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCS8450 5.903 ms 0 - 197 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 4.303 ms 0 - 10 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 48.403 ms 0 - 188 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 6.22 ms 0 - 170 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 2.15 ms 0 - 174 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8295P 6.03 ms 0 - 166 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 6.22 ms 0 - 170 MB NPU

License

  • The license for the original implementation of DeepLabV3-Plus-MobileNet 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

Model tree for qualcomm/DeepLabV3-Plus-MobileNet

Finetunes
1 model

Paper for qualcomm/DeepLabV3-Plus-MobileNet