|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:achieved_top5_accuracy
|
89.8% on Image Net
|
|
gptkbp:architecture
|
gptkb:Deep_Learning
|
|
gptkbp:coat_of_arms
|
16 or 19
|
|
gptkbp:developed_by
|
gptkb:Visual_Geometry_Group
|
|
gptkbp:has_variants
|
gptkb:VGG16
gptkb:VGG19
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
VGGNet
|
|
gptkbp:input_output
|
224x224
|
|
gptkbp:is_a_framework_for
|
gptkb:Tensor_Flow
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:is_based_on
|
Convolutional layers
|
|
gptkbp:is_evaluated_by
|
gptkb:CIFAR-10
gptkb:Pascal_VOC
gptkb:COCO
gptkb:Celeb_A_dataset
gptkb:CIFAR-100
LFW dataset
|
|
gptkbp:is_influenced_by
|
gptkb:Le_Net
gptkb:Alex_Net
|
|
gptkbp:is_known_for
|
High accuracy
Feature extraction
Depth of network
Simplicity of architecture
Use of small filters
|
|
gptkbp:is_popular_in
|
gptkb:Computer_Vision
|
|
gptkbp:is_trained_in
|
gptkb:Image_Net_dataset
Data augmentation
Stochastic gradient descent
Dropout regularization
|
|
gptkbp:is_used_in
|
gptkb:virtual_reality
Natural language processing
Sentiment analysis
Speech recognition
Augmented reality
Image segmentation
Anomaly detection
Transfer learning
Autonomous driving
Facial recognition
Video analysis
Recommendation systems
Text recognition
Object detection
Gesture recognition
Style transfer
Medical image analysis
Scene understanding
Image super-resolution
Action recognition
|
|
gptkbp:notable_for
|
Image classification tasks
|
|
gptkbp:performance
|
71.3% on Image Net
|
|
gptkbp:predecessor
|
gptkb:Alex_Net
|
|
gptkbp:successor
|
gptkb:Res_Net
|
|
gptkbp:uses
|
Re LU activation function
|
|
gptkbp:uses_normalization
|
Batch normalization
|
|
gptkbp:uses_pooling
|
Max pooling
|
|
gptkbp:year_established
|
gptkb:2014
|
|
gptkbp:bfsParent
|
gptkb:Image_Net
gptkb:neural_networks
|
|
gptkbp:bfsLayer
|
4
|