DeepLab-V3(ResNet) is a powerful semantic segmentation model that combines the DeepLab-V3 architecture with a ResNet backbone. DeepLab-V3 enhances segmentation accuracy by using Atrous Spatial Pyramid Pooling (ASPP) and an encoder-decoder structure, which are effective in extracting multi-scale features and performing precise segmentation in complex scenes. ResNet, serving as the backbone, leverages residual connections to mitigate the vanishing gradient problem in deep networks, enabling efficient learning of deep image features. This combined model excels in semantic segmentation tasks and is widely applied in areas like autonomous driving, medical image segmentation, and urban scene understanding, providing accurate segmentation in challenging images.

Source model

• Input shape: 520x520
• Number of parameters: 40.06M
• Model size: 160.16M
• Output shape: 1x21x520x520

Source model repository: DeepLab-V3 (ResNet)

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