
VGG16 is a convolutional neural network model proposed by the Visual Geometry Group (VGG) at the University of Oxford in 2014. The model is known for its depth and simple architecture. VGG16 consists of 16 layers, including 13 convolutional layers and 3 fully connected layers. It uses small 3x3 convolutional kernels stacked to increase the network depth, effectively capturing local image features while keeping computational load relatively low. VGG16 performed exceptionally well on the ImageNet image classification task and has served as a foundational architecture for many subsequent models. Although it has a large number of parameters, VGG16’s straightforward design makes it easy to adapt for other computer vision tasks.
Source model
- Input shape: 224x224
- Number of parameters: 132.94M
- Model size: 527.8M
- Output shape 1x1000
Source model repository: VGG16
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