Hugging Face's logo

qualcomm
/
DeepLabXception

Image Segmentation
PyTorch
bu_auto
android
Model card Files
xet
 Community
DeepLabXception / README.md
qaihm-bot's picture
qaihm-bot
v0.59.0
8d8972f verified
preview code
|
Raw
History Blame Contribute Delete
13.3 kB
metadata 
library_name: pytorch
license: other
tags:
  - bu_auto
  - android
pipeline_tag: image-segmentation

DeepLabXception: Optimized for Qualcomm Devices

DeepLabXception is a semantic segmentation model supporting multiple backbones like ResNet-101 and Xception, with flexible dataset compatibility including COCO, VOC, and Cityscapes.

This is based on the implementation of DeepLabXception 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
TFLITE w8a8 Universal QAIRT 2.45 Download

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

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: COCO_WITH_VOC_LABELS_V1
  • Input resolution: 480x520
  • Number of output classes: 21
  • Number of parameters: 41.26M
  • Model size (float): 158 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DeepLabXception ONNX float Snapdragon® X2 Elite 10.416 ms 3 - 3 MB NPU
DeepLabXception ONNX float Snapdragon® X Elite 23.036 ms 86 - 86 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Gen 3 Mobile 17.073 ms 0 - 356 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Gen 1 Mobile 49.996 ms 4 - 356 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 23.03 ms 0 - 95 MB NPU
DeepLabXception ONNX float Qualcomm® QCS8450 49.996 ms 4 - 356 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ IQ-9075 34.389 ms 3 - 8 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ IQ-X7181 23.036 ms 86 - 86 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ Q-8750 13.114 ms 2 - 249 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Elite Mobile 13.114 ms 2 - 249 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Elite Gen 5 Mobile 8.905 ms 2 - 255 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® X2 Elite 3.4 ms 2 - 2 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® X Elite 7.732 ms 44 - 44 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 5.283 ms 1 - 388 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 12.702 ms 0 - 377 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 45.874 ms 0 - 4 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.449 ms 0 - 50 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® QCS8450 12.702 ms 0 - 377 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 7.332 ms 0 - 4 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 7.732 ms 44 - 44 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 4.218 ms 0 - 288 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Elite Mobile 4.218 ms 0 - 288 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.167 ms 0 - 298 MB NPU
DeepLabXception QNN_DLC float Snapdragon® X2 Elite 11.523 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Snapdragon® X Elite 22.968 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Gen 3 Mobile 16.035 ms 1 - 357 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Gen 1 Mobile 45.83 ms 3 - 355 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ QCS8275 112.936 ms 2 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 22.014 ms 3 - 5 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8775P 30.624 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8650P 30.624 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8255P 30.624 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® QCS8450 45.83 ms 3 - 355 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 30.941 ms 3 - 8 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 22.968 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ Q-8750 12.355 ms 3 - 252 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA7255P 112.936 ms 2 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8295P 39.132 ms 0 - 239 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Elite Mobile 12.355 ms 3 - 252 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 9.651 ms 3 - 260 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® X2 Elite 3.887 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® X Elite 8.573 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 5.539 ms 1 - 372 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 13.853 ms 1 - 368 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 46.191 ms 2 - 5 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8275 20.371 ms 1 - 283 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.87 ms 1 - 3 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8775P 8.058 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8650P 8.058 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8255P 8.058 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® QCS8450 13.853 ms 1 - 368 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 7.763 ms 1 - 3 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 8.573 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 93.779 ms 1 - 303 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 12.454 ms 1 - 277 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 4.364 ms 1 - 291 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA7255P 20.371 ms 1 - 283 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8295P 12.733 ms 0 - 279 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 4.364 ms 1 - 291 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.283 ms 1 - 281 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 12.454 ms 1 - 277 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Gen 3 Mobile 16.2 ms 0 - 455 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Gen 1 Mobile 45.527 ms 0 - 455 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ QCS8275 113.216 ms 1 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 21.435 ms 0 - 3 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8775P 30.605 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8650P 30.605 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8255P 30.605 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® QCS8450 45.527 ms 0 - 455 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ IQ-9075 30.823 ms 0 - 93 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ Q-8750 12.334 ms 0 - 353 MB NPU
DeepLabXception TFLITE float Qualcomm® SA7255P 113.216 ms 1 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8295P 38.738 ms 0 - 336 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Elite Mobile 12.334 ms 0 - 353 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 9.286 ms 0 - 353 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 5.0 ms 0 - 368 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 12.048 ms 0 - 360 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 44.459 ms 0 - 58 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ QCS8275 19.018 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.933 ms 0 - 3 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8775P 7.27 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8650P 7.27 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8255P 7.27 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® QCS8450 12.048 ms 0 - 360 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 7.738 ms 0 - 47 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 100.32 ms 0 - 291 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 12.071 ms 0 - 266 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 3.901 ms 0 - 275 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA7255P 19.018 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8295P 11.614 ms 0 - 276 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Elite Mobile 3.901 ms 0 - 275 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.91 ms 0 - 286 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 12.071 ms 0 - 266 MB NPU

License

  • The license for the original implementation of DeepLabXception can be found here.

References

Community