|
gptkbp:instanceOf
|
gptkb:convolutional_neural_network
|
|
gptkbp:activatedBy
|
gptkb:ReLU
|
|
gptkbp:application
|
feature extraction
image classification
object detection
|
|
gptkbp:architectureDepths
|
gptkb:VGG-11
gptkb:VGG-13
gptkb:VGG-16
gptkb:VGG-19
|
|
gptkbp:arXivID
|
gptkb:1409.1556
|
|
gptkbp:author
|
gptkb:Andrew_Zisserman
gptkb:Karen_Simonyan
|
|
gptkbp:category
|
gptkb:model
computer vision
|
|
gptkbp:developedBy
|
gptkb:University_of_Oxford
gptkb:Visual_Geometry_Group
|
|
gptkbp:influenced
|
gptkb:ResNet
gptkb:DenseNet
|
|
gptkbp:inputImageSize
|
224x224
|
|
gptkbp:introducedIn
|
gptkb:ImageNet_Large_Scale_Visual_Recognition_Challenge_2014
2014
|
|
gptkbp:notableFor
|
improved image classification performance
use of small 3x3 convolution filters
very deep convolutional networks
|
|
gptkbp:notablePublication
|
gptkb:Very_Deep_Convolutional_Networks_for_Large-Scale_Image_Recognition
|
|
gptkbp:parameter
|
~138 million (VGG-16)
|
|
gptkbp:platform
|
gptkb:TensorFlow
gptkb:Keras
gptkb:PyTorch
|
|
gptkbp:poolingType
|
max pooling
|
|
gptkbp:trainer
|
gptkb:ImageNet
|
|
gptkbp:bfsParent
|
gptkb:Computer_Vision
gptkb:ImageNet_dataset
gptkb:ImageNet
|
|
gptkbp:bfsLayer
|
6
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
VGGNet
|