|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:characterized_by
|
Deep Convolutional Layers
|
|
gptkbp:depth
|
16 layers for VGG16
19 layers for VGG19
|
|
gptkbp:developed_by
|
gptkb:University_of_Oxford
gptkb:Visual_Geometry_Group
|
|
gptkbp:has_input_size
|
224x224
|
|
gptkbp:has_output_layer
|
Softmax Layer
|
|
gptkbp:has_pooling_layer
|
Max Pooling
|
|
gptkbp:has_variants
|
gptkb:VGG16
gptkb:VGG19
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
VGG Architecture
|
|
gptkbp:initiated_by
|
Re LU
|
|
gptkbp:introduced_in
|
gptkb:2014
|
|
gptkbp:is_adopted_by
|
Kaggle Competitions
|
|
gptkbp:is_based_on
|
Small 3x3 Convolution Filters
|
|
gptkbp:is_cited_in
|
Research Papers
|
|
gptkbp:is_compared_to
|
gptkb:Dense_Net
gptkb:Res_Net
|
|
gptkbp:is_evaluated_by
|
gptkb:Image_Net_Dataset
Top-1 Accuracy
Top-5 Accuracy
|
|
gptkbp:is_implemented_in
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_influenced_by
|
gptkb:Goog_Le_Net
gptkb:Alex_Net
|
|
gptkbp:is_known_for
|
gptkb:Simplicity
Feature Maps
Pooling Layers
High Accuracy
Modularity
|
|
gptkbp:is_part_of
|
gptkb:Computer_Vision
gptkb:Artificial_Intelligence
Deep Learning Models
|
|
gptkbp:is_popular_in
|
gptkb:stage_adaptation
|
|
gptkbp:is_supported_by
|
Pre-trained Models
|
|
gptkbp:is_trained_in
|
Large Datasets
|
|
gptkbp:is_used_in
|
gptkb:art
Object Detection
Facial Recognition
Image Segmentation
Feature Extraction
Video Analysis
Scene Recognition
Medical Image Analysis
|
|
gptkbp:performance
|
Image Classification Tasks
71.3% on Image Net
|
|
gptkbp:used_for
|
Image Classification
|
|
gptkbp:uses_dropout
|
To prevent overfitting
|
|
gptkbp:uses_weight_initialization
|
Xavier Initialization
|
|
gptkbp:bfsParent
|
gptkb:VGG16_with_Batch_Normalization
|
|
gptkbp:bfsLayer
|
7
|