Hugging Face's logo

qualcomm
/
DeepLabV3-Plus-MobileNet

Image Segmentation
PyTorch
LiteRT
android
Model card Files Community
DeepLabV3-Plus-MobileNet / README.md
qaihm-bot's picture
qaihm-bot
v0.37.0
b4a472a verified
preview code
|
raw
history blame contribute delete
27.6 kB
 ---
library_name: pytorch
license: other
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 Mobile Deployment
## Deep Convolutional Neural Network model for semantic segmentation
DeepLabV3 is designed for semantic segmentation at multiple scales, trained on the various datasets. It uses MobileNet as a backbone.
This model is an implementation of DeepLabV3-Plus-MobileNet found [here](https://github.com/jfzhang95/pytorch-deeplab-xception).
This repository provides scripts to run DeepLabV3-Plus-MobileNet on Qualcomm® devices.
More details on model performance across various devices, can be found
[here](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet).
### 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
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| DeepLabV3-Plus-MobileNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 62.712 ms | 0 - 30 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 58.573 ms | 2 - 34 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 19.289 ms | 0 - 43 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 18.756 ms | 3 - 56 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 13.043 ms | 0 - 12 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 11.063 ms | 3 - 18 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 10.728 ms | 0 - 33 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx.zip) |
| DeepLabV3-Plus-MobileNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 19.562 ms | 0 - 31 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 17.411 ms | 2 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 62.712 ms | 0 - 30 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 58.573 ms | 2 - 34 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 13.094 ms | 0 - 12 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 11.064 ms | 3 - 16 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 22.2 ms | 0 - 36 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 19.035 ms | 3 - 54 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 13.062 ms | 0 - 13 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 11.06 ms | 3 - 20 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 19.562 ms | 0 - 31 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 17.411 ms | 2 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 13.092 ms | 0 - 14 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 11.058 ms | 4 - 18 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 10.927 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx.zip) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 9.14 ms | 0 - 49 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 7.97 ms | 3 - 47 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 7.483 ms | 1 - 42 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx.zip) |
| DeepLabV3-Plus-MobileNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.606 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
| DeepLabV3-Plus-MobileNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 7.407 ms | 3 - 65 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 7.399 ms | 4 - 41 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx.zip) |
| DeepLabV3-Plus-MobileNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 11.913 ms | 20 - 20 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.dlc) |
| DeepLabV3-Plus-MobileNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 10.544 ms | 11 - 11 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 22.261 ms | 2 - 45 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 11.185 ms | 2 - 61 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.811 ms | 2 - 17 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.385 ms | 2 - 45 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 44.35 ms | 2 - 112 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 22.261 ms | 2 - 45 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 8.816 ms | 2 - 18 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 13.384 ms | 2 - 52 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 8.837 ms | 2 - 17 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 9.385 ms | 2 - 45 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.83 ms | 2 - 17 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.362 ms | 2 - 62 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.203 ms | 2 - 50 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 9.557 ms | 0 - 0 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a16.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 11.917 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.64 ms | 1 - 38 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.449 ms | 0 - 51 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 6.404 ms | 1 - 53 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.92 ms | 0 - 16 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.124 ms | 1 - 12 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 97.991 ms | 67 - 237 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.474 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.942 ms | 1 - 37 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 17.888 ms | 0 - 43 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 19.911 ms | 1 - 55 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 556.229 ms | 96 - 110 MB | CPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 172.74 ms | 3 - 6 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 551.027 ms | 94 - 104 MB | CPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 11.917 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 10.64 ms | 1 - 38 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.915 ms | 0 - 16 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.135 ms | 1 - 13 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 7.202 ms | 0 - 42 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 6.351 ms | 1 - 45 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.912 ms | 0 - 16 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.141 ms | 1 - 11 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.474 ms | 0 - 35 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.942 ms | 1 - 37 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.916 ms | 0 - 12 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.139 ms | 2 - 12 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 96.553 ms | 67 - 238 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.488 ms | 0 - 49 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.846 ms | 1 - 55 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 80.026 ms | 46 - 2533 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.628 ms | 0 - 41 MB | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.tflite) |
| DeepLabV3-Plus-MobileNet | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.564 ms | 1 - 49 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 79.497 ms | 89 - 752 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
| DeepLabV3-Plus-MobileNet | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.568 ms | 9 - 9 MB | NPU | [DeepLabV3-Plus-MobileNet.dlc](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.dlc) |
| DeepLabV3-Plus-MobileNet | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 111.716 ms | 133 - 133 MB | NPU | [DeepLabV3-Plus-MobileNet.onnx.zip](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet_w8a8.onnx.zip) |
## Installation
Install the package via pip:
```bash
pip install qai-hub-models
```
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
With this API token, you can configure your client to run models on the cloud
hosted devices.
```bash
qai-hub configure --api_token API_TOKEN
```
Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
## Demo off target
The package contains a simple end-to-end demo that downloads pre-trained
weights and runs this model on a sample input.
```bash
python -m qai_hub_models.models.deeplabv3_plus_mobilenet.demo
```
The above demo runs a reference implementation of pre-processing, model
inference, and post processing.
**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
environment, please add the following to your cell (instead of the above).
```
%run -m qai_hub_models.models.deeplabv3_plus_mobilenet.demo
```
### Run model on a cloud-hosted device
In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
device. This script does the following:
* Performance check on-device on a cloud-hosted device
* Downloads compiled assets that can be deployed on-device for Android.
* Accuracy check between PyTorch and on-device outputs.
```bash
python -m qai_hub_models.models.deeplabv3_plus_mobilenet.export
```
## How does this work?
This [export script](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet/qai_hub_models/models/DeepLabV3-Plus-MobileNet/export.py)
leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
on-device. Lets go through each step below in detail:
Step 1: **Compile model for on-device deployment**
To compile a PyTorch model for on-device deployment, we first trace the model
in memory using the `jit.trace` and then call the `submit_compile_job` API.
```python
import torch
import qai_hub as hub
from qai_hub_models.models.deeplabv3_plus_mobilenet import Model
# Load the model
torch_model = Model.from_pretrained()
# Device
device = hub.Device("Samsung Galaxy S24")
# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()
pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
# Compile model on a specific device
compile_job = hub.submit_compile_job(
model=pt_model,
device=device,
input_specs=torch_model.get_input_spec(),
)
# Get target model to run on-device
target_model = compile_job.get_target_model()
```
Step 2: **Performance profiling on cloud-hosted device**
After compiling models from step 1. Models can be profiled model on-device using the
`target_model`. Note that this scripts runs the model on a device automatically
provisioned in the cloud. Once the job is submitted, you can navigate to a
provided job URL to view a variety of on-device performance metrics.
```python
profile_job = hub.submit_profile_job(
model=target_model,
device=device,
)
```
Step 3: **Verify on-device accuracy**
To verify the accuracy of the model on-device, you can run on-device inference
on sample input data on the same cloud hosted device.
```python
input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
model=target_model,
device=device,
inputs=input_data,
)
on_device_output = inference_job.download_output_data()
```
With the output of the model, you can compute like PSNR, relative errors or
spot check the output with expected output.
**Note**: This on-device profiling and inference requires access to Qualcomm®
AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
## Run demo on a cloud-hosted device
You can also run the demo on-device.
```bash
python -m qai_hub_models.models.deeplabv3_plus_mobilenet.demo --eval-mode on-device
```
**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
environment, please add the following to your cell (instead of the above).
```
%run -m qai_hub_models.models.deeplabv3_plus_mobilenet.demo -- --eval-mode on-device
```
## Deploying compiled model to Android
The models can be deployed using multiple runtimes:
- TensorFlow Lite (`.tflite` export): [This
tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
guide to deploy the .tflite model in an Android application.
- QNN (`.so` export ): This [sample
app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
provides instructions on how to use the `.so` shared library in an Android application.
## View on Qualcomm® AI Hub
Get more details on DeepLabV3-Plus-MobileNet's performance across various devices [here](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet).
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
## 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).
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
## 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:[email protected]).