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 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	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® 8 Elite Gen 5 Mobile	8.748 ms	3 - 254 MB	NPU
DeepLabXception	ONNX	float	Snapdragon® X2 Elite	10.317 ms	86 - 86 MB	NPU
DeepLabXception	ONNX	float	Snapdragon® X Elite	22.693 ms	85 - 85 MB	NPU
DeepLabXception	ONNX	float	Snapdragon® 8 Gen 3 Mobile	16.739 ms	0 - 362 MB	NPU
DeepLabXception	ONNX	float	Qualcomm® QCS8550 (Proxy)	22.447 ms	0 - 375 MB	NPU
DeepLabXception	ONNX	float	Qualcomm® QCS9075	32.515 ms	3 - 8 MB	NPU
DeepLabXception	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	13.121 ms	1 - 241 MB	NPU
DeepLabXception	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	3.06 ms	0 - 293 MB	NPU
DeepLabXception	ONNX	w8a8	Snapdragon® X2 Elite	3.351 ms	44 - 44 MB	NPU
DeepLabXception	ONNX	w8a8	Snapdragon® X Elite	8.012 ms	44 - 44 MB	NPU
DeepLabXception	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	5.301 ms	0 - 390 MB	NPU
DeepLabXception	ONNX	w8a8	Qualcomm® QCS6490	308.978 ms	89 - 117 MB	CPU
DeepLabXception	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	7.466 ms	0 - 51 MB	NPU
DeepLabXception	ONNX	w8a8	Qualcomm® QCS9075	7.645 ms	0 - 4 MB	NPU
DeepLabXception	ONNX	w8a8	Qualcomm® QCM6690	243.516 ms	56 - 68 MB	CPU
DeepLabXception	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	4.223 ms	1 - 289 MB	NPU
DeepLabXception	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	229.03 ms	89 - 102 MB	CPU
DeepLabXception	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	9.241 ms	3 - 258 MB	NPU
DeepLabXception	QNN_DLC	float	Snapdragon® X2 Elite	11.169 ms	3 - 3 MB	NPU
DeepLabXception	QNN_DLC	float	Snapdragon® X Elite	22.764 ms	3 - 3 MB	NPU
DeepLabXception	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	16.091 ms	0 - 366 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	113.166 ms	2 - 246 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	21.892 ms	3 - 34 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® SA8775P	30.591 ms	1 - 245 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® QCS9075	35.246 ms	3 - 8 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	45.546 ms	0 - 361 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® SA7255P	113.166 ms	2 - 246 MB	NPU
DeepLabXception	QNN_DLC	float	Qualcomm® SA8295P	38.898 ms	0 - 242 MB	NPU
DeepLabXception	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	12.212 ms	0 - 252 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	3.263 ms	1 - 274 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® X2 Elite	3.879 ms	1 - 1 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® X Elite	8.535 ms	1 - 1 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	5.519 ms	1 - 374 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCS6490	33.447 ms	1 - 3 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	20.344 ms	1 - 281 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	7.895 ms	1 - 2 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® SA8775P	8.092 ms	1 - 284 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCS9075	8.594 ms	1 - 3 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCM6690	94.111 ms	1 - 303 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	14.188 ms	1 - 367 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® SA7255P	20.344 ms	1 - 281 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Qualcomm® SA8295P	12.687 ms	1 - 276 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	4.37 ms	1 - 274 MB	NPU
DeepLabXception	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	12.319 ms	1 - 276 MB	NPU
DeepLabXception	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	9.227 ms	0 - 369 MB	NPU
DeepLabXception	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	16.191 ms	0 - 481 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® QCS8275 (Proxy)	113.23 ms	0 - 358 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® QCS8550 (Proxy)	21.853 ms	0 - 3 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® SA8775P	30.588 ms	0 - 357 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® QCS9075	35.057 ms	0 - 93 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® QCS8450 (Proxy)	46.669 ms	0 - 472 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® SA7255P	113.23 ms	0 - 358 MB	NPU
DeepLabXception	TFLITE	float	Qualcomm® SA8295P	38.655 ms	0 - 349 MB	NPU
DeepLabXception	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	12.221 ms	0 - 365 MB	NPU
DeepLabXception	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	2.897 ms	0 - 268 MB	NPU
DeepLabXception	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	4.94 ms	0 - 373 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCS6490	32.019 ms	0 - 58 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	18.892 ms	0 - 284 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	7.1 ms	0 - 3 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® SA8775P	7.245 ms	0 - 284 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCS9075	7.45 ms	0 - 47 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCM6690	91.711 ms	0 - 295 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	11.838 ms	0 - 360 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® SA7255P	18.892 ms	0 - 284 MB	NPU
DeepLabXception	TFLITE	w8a8	Qualcomm® SA8295P	11.553 ms	0 - 273 MB	NPU
DeepLabXception	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	3.928 ms	0 - 274 MB	NPU
DeepLabXception	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	11.522 ms	0 - 268 MB	NPU

License

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

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/DeepLabXception

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Paper • 1802.02611 • Published Feb 7, 2018