AlexNet is a convolutional neural network model introduced in 2012 by Alex Krizhevsky and his team. It achieved remarkable success in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and is considered a milestone that sparked the modern deep learning revolution. AlexNet consists of five convolutional layers and three fully connected layers, utilizing the ReLU activation function to speed up training and employing Dropout to prevent overfitting. The model also leveraged GPU parallel computing to significantly improve training speed. AlexNet’s design greatly improved the accuracy of image classification tasks, marking the widespread adoption of convolutional neural networks in computer vision.

Source model

• Input shape: 224x224
• Number of parameters: 58.27M
• Model size: 233.08M
• Output shape: 1x1000

Source model repository: AlexNet

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