---
library_name: pytorch
license: mit
tags:
- android
pipeline_tag: image-segmentation

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/web-assets/model_demo.png)

# 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](https://github.com/jfzhang95/pytorch-deeplab-xception).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/deeplabv3_plus_mobilenet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-onnx-w8a16.zip)
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-qnn_dlc-w8a16.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deeplabv3_plus_mobilenet/releases/v0.61.0/deeplabv3_plus_mobilenet-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[DeepLabV3-Plus-MobileNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/deeplabv3_plus_mobilenet) 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](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/deeplabv3_plus_mobilenet) 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® X2 Elite | 5.197 ms | 3 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Snapdragon® X Elite | 10.83 ms | 10 - 10 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.988 ms | 4 - 203 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.996 ms | 4 - 209 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 17.373 ms | 3 - 7 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.281 ms | 0 - 13 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® QCS8450 | 17.996 ms | 4 - 209 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 17.295 ms | 3 - 6 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.83 ms | 10 - 10 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 5.983 ms | 1 - 168 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Snapdragon® 8 Elite Mobile | 5.983 ms | 1 - 168 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.344 ms | 1 - 173 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® X2 Elite | 3.45 ms | 2 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® X Elite | 7.385 ms | 5 - 5 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.112 ms | 2 - 214 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.4 ms | 2 - 216 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 35.951 ms | 2 - 4 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.388 ms | 2 - 5 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.991 ms | 0 - 8 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® QCS8450 | 9.4 ms | 2 - 216 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.206 ms | 2 - 4 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.385 ms | 5 - 5 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 108.899 ms | 2 - 234 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 12.69 ms | 2 - 187 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.862 ms | 0 - 184 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.862 ms | 0 - 184 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.779 ms | 0 - 190 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 12.69 ms | 2 - 187 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® X2 Elite | 1.586 ms | 2 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® X Elite | 3.652 ms | 6 - 6 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.408 ms | 0 - 201 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 5.014 ms | 1 - 203 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 16.378 ms | 1 - 4 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) | 3.465 ms | 0 - 8 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® QCS8450 | 5.014 ms | 1 - 203 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 4.423 ms | 1 - 4 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 3.652 ms | 6 - 6 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 47.308 ms | 1 - 203 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 5.62 ms | 1 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.904 ms | 0 - 179 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 1.904 ms | 0 - 179 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.409 ms | 0 - 182 MB | NPU
| DeepLabV3-Plus-MobileNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 5.62 ms | 1 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® X2 Elite | 7.687 ms | 3 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® X Elite | 12.473 ms | 3 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.086 ms | 0 - 206 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.897 ms | 3 - 208 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 18.791 ms | 3 - 9 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 58.602 ms | 2 - 167 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.557 ms | 3 - 5 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® SA8775P | 17.521 ms | 1 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® SA8650P | 17.521 ms | 1 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® SA8255P | 17.521 ms | 1 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® QCS8450 | 19.897 ms | 3 - 208 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 18.053 ms | 3 - 8 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.473 ms | 3 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.285 ms | 3 - 180 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® SA7255P | 58.602 ms | 2 - 167 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Qualcomm® SA8295P | 19.563 ms | 0 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 6.285 ms | 3 - 180 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.386 ms | 3 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.3 ms | 2 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.228 ms | 2 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.129 ms | 2 - 214 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 12.131 ms | 2 - 215 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 39.885 ms | 1 - 4 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 8.806 ms | 2 - 6 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 21.993 ms | 2 - 182 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.394 ms | 2 - 4 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® SA8775P | 8.929 ms | 2 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® SA8650P | 8.929 ms | 2 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® SA8255P | 8.929 ms | 2 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 12.131 ms | 2 - 215 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 9.484 ms | 3 - 7 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 9.228 ms | 2 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 94.316 ms | 4 - 235 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 11.643 ms | 0 - 179 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.353 ms | 1 - 180 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® SA7255P | 21.993 ms | 2 - 182 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Qualcomm® SA8295P | 13.732 ms | 2 - 197 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 4.353 ms | 1 - 180 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.136 ms | 1 - 198 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 11.643 ms | 0 - 179 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 2.108 ms | 1 - 1 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 4.629 ms | 1 - 1 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.912 ms | 0 - 195 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 6.653 ms | 1 - 196 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 18.052 ms | 3 - 5 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 4.222 ms | 0 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.8 ms | 1 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.171 ms | 1 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 4.694 ms | 1 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 4.694 ms | 1 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 4.694 ms | 1 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 6.653 ms | 1 - 196 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 4.47 ms | 1 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 4.629 ms | 1 - 1 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 49.203 ms | 1 - 201 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 6.278 ms | 1 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 2.188 ms | 1 - 172 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 10.8 ms | 1 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 6.398 ms | 1 - 168 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 2.188 ms | 1 - 172 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.635 ms | 1 - 178 MB | NPU
| DeepLabV3-Plus-MobileNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 6.278 ms | 1 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.092 ms | 0 - 212 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.843 ms | 0 - 212 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 18.577 ms | 0 - 19 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 58.651 ms | 0 - 168 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.524 ms | 0 - 2 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® SA8775P | 17.553 ms | 0 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® SA8650P | 17.553 ms | 0 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® SA8255P | 17.553 ms | 0 - 171 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® QCS8450 | 19.843 ms | 0 - 212 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 17.362 ms | 0 - 18 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 6.298 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® SA7255P | 58.651 ms | 0 - 168 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Qualcomm® SA8295P | 19.636 ms | 0 - 169 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 6.298 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.393 ms | 0 - 183 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.944 ms | 0 - 202 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 5.771 ms | 0 - 201 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 18.839 ms | 0 - 11 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 4.405 ms | 0 - 10 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.825 ms | 0 - 174 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.323 ms | 0 - 3 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® SA8775P | 4.621 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® SA8650P | 4.621 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® SA8255P | 4.621 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 5.771 ms | 0 - 201 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 4.395 ms | 0 - 10 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 50.346 ms | 0 - 195 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 6.418 ms | 0 - 177 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 2.082 ms | 0 - 175 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® SA7255P | 10.825 ms | 0 - 174 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Qualcomm® SA8295P | 6.229 ms | 0 - 172 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 2.082 ms | 0 - 175 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.612 ms | 0 - 184 MB | NPU
| DeepLabV3-Plus-MobileNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 6.418 ms | 0 - 177 MB | NPU

## License
* The license for the original implementation of DeepLabV3-Plus-MobileNet can be found
  [here](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/LICENSE).

## References
* [Rethinking Atrous Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1706.05587)
* [Source Model Implementation](https://github.com/jfzhang95/pytorch-deeplab-xception)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).