SqueezeNet is a lightweight convolutional neural network model introduced by Forrest Iandola and his team in 2016, designed to reduce the number of model parameters while maintaining high accuracy in image classification tasks. The core innovation in SqueezeNet is the "Fire Module," which reduces parameters through a two-step process: first "squeezing" the input with 1x1 convolutions to reduce the number of channels, and then "expanding" it with a mix of 1x1 and 3x3 convolutions. This architecture drastically reduces the model's parameter count compared to traditional convolutional networks while preserving high accuracy. SqueezeNet is particularly well-suited for devices with limited computational resources, such as mobile devices and embedded systems, enabling efficient image classification and object detection in such environments.

Source model

• Input shape: 224x224
• Number of parameters: 1.19M
• Model size: 4.78M
• Output shape: 1x1000

Source model repository: Squeezenet

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