DeepLab-V3-Plus (MobileNet) is a lightweight semantic segmentation model that combines the DeepLab-V3-Plus architecture with MobileNet. DeepLab-V3-Plus is an advanced framework for semantic segmentation, using Atrous Spatial Pyramid Pooling (ASPP) and an encoder-decoder structure to improve segmentation accuracy. MobileNet, known for its efficiency, reduces computational complexity and model size. By using MobileNet as the backbone of DeepLab-V3-Plus, this model can perform high-quality semantic segmentation on mobile or edge devices with limited computational resources. It is widely used in real-time segmentation tasks such as autonomous driving, medical image analysis, and augmented reality.

Source model

• Input shape: 513x513
• Number of parameters: 5.55M
• Model size: 22.16M
• Output shape: 1x21x513x513

Source model repository: DeepLab-V3-Plus (MobileNet)

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md