|
gptkbp:instance_of
|
gptkb:television_channel
|
|
gptkbp:applies_to
|
Image Classification
|
|
gptkbp:architectural_style
|
gptkb:Deep_Learning
|
|
gptkbp:coat_of_arms
|
201
|
|
gptkbp:developed_by
|
Gao Huang
|
|
gptkbp:has
|
Fully Connected Layer
Dense Blocks
Global Average Pooling Layer
Transition Layers
|
|
gptkbp:has_achievements
|
High Accuracy
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Dense Net-201
|
|
gptkbp:is_compared_to
|
gptkb:Res_Net
|
|
gptkbp:is_evaluated_by
|
Robustness
Generalization Ability
Top-1 Accuracy
Top-5 Accuracy
|
|
gptkbp:is_implemented_in
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_influenced_by
|
gptkb:Inception_Network
VGG Net
|
|
gptkbp:is_known_for
|
Reducing Overfitting
Improved Gradient Flow
Feature Reuse
High Parameter Efficiency
Improving Model Interpretability
|
|
gptkbp:is_optimized_for
|
Memory Efficiency
|
|
gptkbp:is_part_of
|
gptkb:viewpoint
gptkb:Artificial_Intelligence
gptkb:Dense_Net_Family
Deep Learning Frameworks
|
|
gptkbp:is_related_to
|
gptkb:streaming_service
Fine-tuning
|
|
gptkbp:is_supported_by
|
NVIDIAGP Us
TP Us
|
|
gptkbp:is_used_in
|
gptkb:Autonomous_Vehicles
gptkb:software
gptkb:studio
gptkb:robot
gptkb:museum
Anomaly Detection
Object Detection
Time Series Analysis
Facial Recognition
Image Restoration
Generative Models
Video Analysis
Semantic Segmentation
Medical Image Analysis
|
|
gptkbp:performance
|
gptkb:Image_Net_Challenge
Visual Recognition Tasks
|
|
gptkbp:training
|
gptkb:Image_Net
gptkb:CIFAR-10
|
|
gptkbp:uses
|
gptkb:Batch_Normalization
gptkb:Dropout
Dense Connectivity
Re LU Activation Function
|
|
gptkbp:year_created
|
gptkb:2017
|
|
gptkbp:bfsParent
|
gptkb:Dense_Net
|
|
gptkbp:bfsLayer
|
4
|