New to Peltarion? Discover our deep learning Platform
A single deep learning platform to build and deploy your projects, even if you’re not an AI superstar.FIND OUT MORE
VGG - pretrained
The VGG (Visual Geometry Group) network greatly influenced the design of deep convolutional neural networks. Although there exist architectures with better performance, VGG is still very useful for many applications such as image classification.
Input image size: 32x32 pixels and larger.
On the Peltarion Platform, the pretrained VGG network is implemented in the following snippet:
VGG16 feature extractor. Same as the VGG16 but without the last part of the model.
The 2D Convolutional blocks all have a 3x3 filter (Width x Height). This is the smallest size to capture the notion of left-right, up-down, and center.
How to use the VGG with weights snippet
The basic idea is that you first create and train an experiment containing a pretrained snippet and some Dense blocks. Only the Dense blocks will be trained in the first experiment.
Then you duplicate this first experiment, set all blocks to trainable and train the new experiment with a really low learning rate.
The method is described in How to use pretrained snippets with weights.
When using pretrained snippets, additonal terms apply: VGG with weights licence.
Karen Simonyan, Andrew Zisserman: Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014.