|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:application
|
gptkb:Augmented_Reality
gptkb:art
gptkb:Autonomous_Vehicles
gptkb:sports_team
gptkb:robotics
Anomaly Detection
Facial Recognition
Medical Imaging
Agricultural Monitoring
Emotion Recognition
Smart Cities
Video Analysis
Wildlife Conservation
Retail Analytics
Gesture Recognition
Scene Understanding
Art Generation
Security Surveillance
Text Recognition
|
|
gptkbp:architecture
|
gptkb:Deep_Learning
|
|
gptkbp:coat_of_arms
|
16 or 19
|
|
gptkbp:dataset_used_for_training
|
gptkb:Image_Net
|
|
gptkbp:developed_by
|
gptkb:Visual_Geometry_Group
|
|
gptkbp:has_achieved
|
Top-5 accuracy on Image Net
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
VGG Networks
|
|
gptkbp:influenced_by
|
gptkb:Goog_Le_Net
gptkb:Alex_Net
|
|
gptkbp:input_output
|
224x224 pixels
|
|
gptkbp:is_a_framework_for
|
gptkb:Tensor_Flow
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:is_popular_in
|
gptkb:Computer_Vision
Deep Learning Community
|
|
gptkbp:notable_applications
|
Object Detection
Image Segmentation
Feature Extraction
|
|
gptkbp:notable_for
|
Image Classification
|
|
gptkbp:notable_traits
|
Depth of network
Small receptive fields
Stacked convolutional layers
Uniform architecture
|
|
gptkbp:performance
|
gptkb:Loss
Accuracy
|
|
gptkbp:pretrained_models_available
|
gptkb:Yes
|
|
gptkbp:requires
|
High computational power
Large dataset
|
|
gptkbp:successor
|
gptkb:VGG16
gptkb:VGG19
|
|
gptkbp:training
|
Long
|
|
gptkbp:uses
|
Max Pooling
Dropout for regularization
Re LU activation function
Softmax layer
|
|
gptkbp:year_established
|
gptkb:2014
|
|
gptkbp:bfsParent
|
gptkb:Res_Ne_Xt
|
|
gptkbp:bfsLayer
|
6
|