|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:architecture
|
Image Classification
|
|
gptkbp:base_model
|
gptkb:Efficient_Net
|
|
gptkbp:designed_for
|
Mobile and Edge Devices
|
|
gptkbp:developed_by
|
gptkb:Google_AI
|
|
gptkbp:flops
|
7.8 billion
|
|
gptkbp:has_achieved
|
State-of-the-art performance on Image Net
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Efficient Net B3
|
|
gptkbp:improves
|
gptkb:Efficient_Net_B2
|
|
gptkbp:initiated_by
|
Swish
|
|
gptkbp:input_output
|
300x300
|
|
gptkbp:is_available_on
|
Model Zoos
|
|
gptkbp:is_compared_to
|
gptkb:Mobile_Net
gptkb:Dense_Net
gptkb:Res_Net
|
|
gptkbp:is_documented_in
|
Research Papers
|
|
gptkbp:is_evaluated_by
|
gptkb:CIFAR-10
gptkb:SVHN
gptkb:Tiny_Image_Net
gptkb:Fashion_MNIST
gptkb:CIFAR-100
Kaggle Competitions
Oxford Pets Dataset
Stanford Dogs Dataset
|
|
gptkbp:is_optimized_for
|
Computational Efficiency
|
|
gptkbp:is_part_of
|
gptkb:Image_Net_Challenge
Efficient Net Family
|
|
gptkbp:is_supported_by
|
Community Contributions
|
|
gptkbp:is_trained_in
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_used_in
|
gptkb:Autonomous_Vehicles
gptkb:sports_team
Chatbots
Object Detection
Facial Recognition
Medical Imaging
Agricultural Monitoring
Social Media Analysis
Gaming Industry
Video Analysis
Content Moderation
Retail Analytics
Personal Assistants
Smartphone Applications
Augmented Reality Applications
Virtual Reality Applications
Security Surveillance
Image Recognition Tasks
E-commerce Recommendations
|
|
gptkbp:orbital_period
|
12 million
|
|
gptkbp:performance
|
Model Compression Techniques
Image Classification Models
|
|
gptkbp:release_year
|
gptkb:2019
|
|
gptkbp:supports
|
gptkb:stage_adaptation
|
|
gptkbp:top1_accuracy
|
81.6%
|
|
gptkbp:top5_accuracy
|
96.5%
|
|
gptkbp:uses
|
Depthwise Separable Convolutions
|
|
gptkbp:bfsParent
|
gptkb:Efficient_Net
|
|
gptkbp:bfsLayer
|
5
|