VGG19 is a deep convolutional neural network introduced by the Visual Geometry Group (VGG) at the University of Oxford in 2014, and it is an enhanced version of the VGG model. VGG19 consists of 19 layers (16 convolutional layers and 3 fully connected layers) and uses small 3x3 convolutional kernels to extract high-level features from images by increasing network depth. The model’s primary characteristics are its simple and consistent structure, where all convolution layers use the same 3x3 kernels and downsampling is achieved through max-pooling layers. VGG19 performed exceptionally well on the ImageNet dataset, and despite its large parameter and computational demands, its high accuracy and transferability have led to its widespread use in various computer vision tasks, including image classification and feature extraction.

Source model

• Input shape: 224x224
• Number of parameters: 137.01M
• Model size: 548.06M
• Output shape 1x1000

Source model repository: VGG19

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