둘러보기로 가기 검색하러 가기
- VGGNet is a Convolutional Neural Network architecture proposed by Karen Simonyan and Andrew Zisserman from the University of Oxford in 2014.
- Another variation of VGGNet has 19 weight layers consisting of 16 convolutional layers with 3 fully connected layers and same 5 pooling layers.
- In both variation of VGGNet there consists of two Fully Connected layers with 4096 channels each which is followed by another fully connected layer with 1000 channels to predict 1000 labels.
- VGGNet is a neural network that performed very well in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2014.
- VGGNet apparently took 2-3 weeks to train on a computer with four NVIDIA Titan Black GPUs.
- Let’s say you want to train a network such as VGGNet to recognize faces of celebrities.
- Since the VGGNet we’re using was trained on ImageNet, it’s really good at distinguishing between different breeds of dogs, different types of fish, and so on.
- VGGNet is invented by Visual Geometry Group (by Oxford University).
- The reason to understand VGGNet is that many modern image classification models are built on top of this architecture.
- It achieves better accuracy than VGGNet and GoogLeNet while being computationally more efficient than VGGNet.
- The architecture is similar to the VGGNet consisting mostly of 3X3 filters.
- From the VGGNet, shortcut connection as described above is inserted to form a residual network.
- VGGNet was a competitor in the ImageNet ILSVRC-2014 image classification competition and scored second place.
- The runner-up in ILSVRC 2014 was the network from Karen Simonyan and Andrew Zisserman that became known as the VGGNet.
- A downside of the VGGNet is that it is more expensive to evaluate and uses a lot more memory and parameters (140M).
- Lets break down the VGGNet in more detail as a case study.
- The whole VGGNet is composed of CONV layers that perform 3x3 convolutions with stride 1 and pad 1, and of POOL layers that perform 2x2 max pooling with stride 2 (and no padding).
- They compare HybridNet, with VGGNet and CBP-CNN, for 292, 100, and 200 sub-classes of VegFru Dataset.
- VGGNet Architecture Explained
- Convolutional neural networks on the iPhone with VGGNet
- What is the VGG neural network?
- ResNet, AlexNet, VGGNet, Inception: Understanding various architectures of Convolutional Networks – CV-Tricks.com
- hollance/VGGNet-Metal: iPhone version of the VGGNet convolutional neural network for image recognition
- CS231n Convolutional Neural Networks for Visual Recognition
- A Review of Convolutional Neural Network Applied to Fruit Image Processing