|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:applies_to
|
Global Average Pooling
|
|
gptkbp:characterized_by
|
Dense Connectivity
|
|
gptkbp:developed_by
|
Gao Huang
|
|
gptkbp:enhances
|
Gradient flow
|
|
gptkbp:has_achieved
|
Higher accuracy
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Dense Net Family
|
|
gptkbp:improves
|
Feature propagation
|
|
gptkbp:includes
|
gptkb:Dense_Net-121
gptkb:Dense_Net-169
gptkb:Dense_Net-201
gptkb:Dense_Net-264
|
|
gptkbp:introduced_in
|
gptkb:2017
|
|
gptkbp:is_adopted_by
|
Research Institutions
Startups
Tech Companies
|
|
gptkbp:is_based_on
|
Convolutional Layers
Pooling Layers
Activation Functions
|
|
gptkbp:is_compared_to
|
gptkb:Res_Net
|
|
gptkbp:is_documented_in
|
Online Courses
Research Papers
Technical Blogs
Git Hub Repositories
|
|
gptkbp:is_evaluated_by
|
gptkb:Image_Net
gptkb:CIFAR-10
gptkb:MNIST
F1 Score
Precision
Recall
Top-1 Accuracy
Top-5 Accuracy
|
|
gptkbp:is_implemented_in
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_known_for
|
High efficiency
Strong performance
|
|
gptkbp:is_optimized_for
|
gptkb:Adam_Optimizer
Stochastic Gradient Descent
|
|
gptkbp:is_popular_in
|
gptkb:Computer_Vision
|
|
gptkbp:is_related_to
|
gptkb:neural_networks
gptkb:stage_adaptation
gptkb:Deep_Learning
|
|
gptkbp:is_supported_by
|
gptkb:NVIDIA_GPUs
gptkb:TPUs
Cloud Computing Platforms
|
|
gptkbp:is_used_in
|
Object Detection
Medical Imaging
Face Recognition
Video Analysis
Scene Recognition
Semantic Segmentation
Image Super-Resolution
Action Recognition
|
|
gptkbp:reduces
|
Number of parameters
|
|
gptkbp:used_for
|
Image Classification
|
|
gptkbp:utilizes
|
Bottleneck layers
|
|
gptkbp:bfsParent
|
gptkb:Dense_Net-121
gptkb:Dense_Net-201
|
|
gptkbp:bfsLayer
|
6
|