ShuffleNet-v2 is an efficient convolutional neural network designed for mobile and embedded devices. It introduces two key strategies: "channel splitting" and "channel shuffling" to optimize performance in resource-constrained environments. Channel splitting reduces computation, while channel shuffling ensures effective information exchange across different groups. Additionally, ShuffleNet-v2 simplifies the network structure, further reducing memory access cost and improving overall inference speed. This model is particularly suitable for tasks like image classification and object detection, significantly lowering computational complexity while maintaining high accuracy.

Source model

• Input shape: 224x224
• Number of parameters: 1.30M
• Model size: 5.26M
• Output shape: 1x1000

Source model repository: Shufflenet-v2

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