|
gptkbp:instance_of
|
gptkb:television_channel
|
|
gptkbp:architectural_style
|
gptkb:Deep_Learning
|
|
gptkbp:based_on
|
gptkb:Res_Net_architecture
|
|
gptkbp:depth
|
50 layers
|
|
gptkbp:developed_by
|
gptkb:Facebook_AI_Research
|
|
gptkbp:has_achievements
|
State-of-the-art performance
|
|
gptkbp:has_method
|
Approximately 25 million
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Res Ne Xt-50
|
|
gptkbp:introduced
|
gptkb:2017
|
|
gptkbp:is_adopted_by
|
Industry applications
|
|
gptkbp:is_available_on
|
gptkb:archive
|
|
gptkbp:is_cited_in
|
Academic literature
|
|
gptkbp:is_compared_to
|
gptkb:Inception
gptkb:Dense_Net
gptkb:Res_Net
|
|
gptkbp:is_documented_in
|
Research papers
Technical reports
Online tutorials
|
|
gptkbp:is_evaluated_by
|
gptkb:Image_Net
gptkb:CIFAR-10
gptkb:CIFAR-100
Face Recognition
Adversarial Examples
Action Recognition
Visual Recognition tasks
|
|
gptkbp:is_implemented_in
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_known_for
|
Scalability
High accuracy
Modular architecture
Robustness to overfitting
Efficient computation
|
|
gptkbp:is_optimized_for
|
GPU training
|
|
gptkbp:is_part_of
|
gptkb:Image_Net_competition
Neural Network architectures
AI research papers
Deep Learning frameworks
AI toolkits
Machine Learning conferences
|
|
gptkbp:is_popular_in
|
gptkb:Research_Institute
|
|
gptkbp:is_related_to
|
gptkb:Residual_Networks
|
|
gptkbp:is_supported_by
|
Community contributions
|
|
gptkbp:is_used_for
|
Image Classification
Object Detection
Data Augmentation
Feature Extraction
Instance Segmentation
Semantic Segmentation
|
|
gptkbp:is_used_in
|
gptkb:Autonomous_Vehicles
gptkb:software
gptkb:robot
Medical Imaging
Real-time applications
Computer Vision tasks
|
|
gptkbp:supports
|
gptkb:streaming_service
|
|
gptkbp:training
|
gptkb:Adam_optimizer
Stochastic Gradient Descent
Large-scale datasets
|
|
gptkbp:uses
|
Cardinality
|
|
gptkbp:utilizes
|
Split-Transform-Merge strategy
|
|
gptkbp:bfsParent
|
gptkb:Res_Ne_Xt
|
|
gptkbp:bfsLayer
|
5
|