Hugging Face's logo

qualcomm
/
DeepLabV3-Plus-MobileNet

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
DeepLabV3-Plus-MobileNet / README.md
qaihm-bot's picture
qaihm-bot
v0.54.0
6415886 verified
preview code
|
raw
history blame contribute delete
16.3 kB
metadata 
library_name: pytorch
license: other
tags:
  - android
pipeline_tag: image-segmentation

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 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 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:

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

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 Mobile 4.304 ms 2 - 177 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Elite Mobile 5.901 ms 1 - 169 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® X2 Elite 5.376 ms 10 - 10 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® X Elite 11.013 ms 10 - 10 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® X Elite 11.013 ms 10 - 10 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Gen 3 Mobile 7.2 ms 4 - 211 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® QCS8550 (Proxy) 10.382 ms 3 - 9 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.901 ms 1 - 169 MB NPU
DeepLabV3-Plus-MobileNet ONNX float Qualcomm® QCS9075 18.048 ms 3 - 6 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.962 ms 0 - 207 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Elite Mobile 3.921 ms 0 - 184 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® X2 Elite 3.707 ms 7 - 7 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® X Elite 7.658 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® X Elite 7.658 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 5.093 ms 2 - 218 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® QCS6490 1224.72 ms 89 - 92 MB CPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 7.099 ms 2 - 4 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® QCM6690 588.837 ms 92 - 101 MB CPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 587.186 ms 92 - 100 MB CPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Qualcomm® QCS9075 8.604 ms 2 - 4 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 3.921 ms 0 - 184 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 587.186 ms 92 - 100 MB CPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.463 ms 0 - 179 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Elite Mobile 1.91 ms 0 - 180 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® X2 Elite 1.664 ms 7 - 7 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® X Elite 3.918 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® X Elite 3.918 ms 5 - 5 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 2.38 ms 0 - 202 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® QCS8550 (Proxy) 3.523 ms 0 - 3 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Qualcomm® QCS9075 4.496 ms 1 - 4 MB NPU
DeepLabV3-Plus-MobileNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.91 ms 0 - 180 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 4.305 ms 3 - 184 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Elite Mobile 6.287 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® X2 Elite 5.578 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® X Elite 12.337 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® X Elite 12.337 ms 3 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 8.077 ms 3 - 212 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® QCS8550 (Proxy) 11.556 ms 3 - 141 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8775P 17.521 ms 1 - 168 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8775P 17.521 ms 1 - 168 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8775P 17.521 ms 1 - 168 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® QCS8450 (Proxy) 19.739 ms 3 - 210 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA7255P 58.62 ms 2 - 167 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 6.287 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® SA8295P 19.609 ms 3 - 172 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC float Qualcomm® QCS9075 20.222 ms 3 - 8 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.073 ms 2 - 195 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 4.327 ms 2 - 180 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® X2 Elite 4.301 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® X Elite 9.133 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® X Elite 9.133 ms 2 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 6.128 ms 2 - 214 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCS6490 33.724 ms 1 - 4 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 8.451 ms 2 - 4 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8775P 8.935 ms 2 - 181 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8775P 8.935 ms 2 - 181 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8775P 8.935 ms 2 - 181 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCM6690 105.929 ms 2 - 234 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 12.254 ms 2 - 215 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 12.042 ms 2 - 181 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® QCS9075 9.733 ms 3 - 7 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA7255P 21.993 ms 2 - 182 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.327 ms 2 - 180 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Qualcomm® SA8295P 13.717 ms 2 - 198 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 12.042 ms 2 - 181 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.618 ms 1 - 176 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 2.196 ms 1 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® X2 Elite 2.069 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® X Elite 4.625 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® X Elite 4.625 ms 1 - 1 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 2.891 ms 1 - 192 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCS6490 15.581 ms 1 - 3 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 4.221 ms 1 - 2 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8775P 4.699 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8775P 4.699 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8775P 4.699 ms 1 - 170 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCS9075 5.134 ms 3 - 5 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 6.648 ms 1 - 197 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.266 ms 1 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® QCM6690 49.769 ms 1 - 202 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.196 ms 1 - 177 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA7255P 10.803 ms 1 - 169 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Qualcomm® SA8295P 6.423 ms 1 - 168 MB NPU
DeepLabV3-Plus-MobileNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.266 ms 1 - 177 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 4.308 ms 0 - 183 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Elite Mobile 6.288 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Gen 3 Mobile 8.067 ms 0 - 215 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® QCS8550 (Proxy) 11.572 ms 0 - 6 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8775P 17.543 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8775P 17.543 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8775P 17.543 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® QCS8450 (Proxy) 19.883 ms 0 - 213 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA7255P 58.646 ms 0 - 169 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 6.288 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® SA8295P 19.621 ms 0 - 170 MB NPU
DeepLabV3-Plus-MobileNet TFLITE float Qualcomm® QCS9075 19.577 ms 0 - 18 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.585 ms 0 - 182 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 2.084 ms 0 - 178 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 2.935 ms 0 - 203 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCS6490 15.838 ms 0 - 11 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 4.366 ms 0 - 37 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8775P 4.606 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8775P 4.606 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8775P 4.606 ms 0 - 176 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCS9075 5.114 ms 0 - 9 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 5.701 ms 0 - 203 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 6.25 ms 0 - 178 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® QCM6690 52.943 ms 0 - 196 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.084 ms 0 - 178 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA7255P 10.814 ms 0 - 173 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Qualcomm® SA8295P 6.244 ms 0 - 172 MB NPU
DeepLabV3-Plus-MobileNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 6.25 ms 0 - 178 MB NPU

License

  • The license for the original implementation of DeepLabV3-Plus-MobileNet can be found here.

References

Community