|
gptkbp:instance_of
|
gptkb:television_channel
|
|
gptkbp:architectural_style
|
Image Classification
|
|
gptkbp:base
|
gptkb:Efficient_Net
|
|
gptkbp:class
|
gptkb:television_series
|
|
gptkbp:developed_by
|
gptkb:Google_AI
|
|
gptkbp:established
|
Swish
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Efficient Net B0
|
|
gptkbp:input_output
|
224x224
|
|
gptkbp:introduced
|
gptkb:2019
|
|
gptkbp:is_available_in
|
gptkb:Graphics_Processing_Unit
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:is_cited_in
|
Dissertations
Research Papers
Conference Presentations
Theses
Technical Blogs
|
|
gptkbp:is_compared_to
|
gptkb:Inception
gptkb:Mobile_Net
gptkb:Dense_Net
gptkb:Res_Net
|
|
gptkbp:is_evaluated_by
|
gptkb:CIFAR-10
gptkb:Stanford_Dogs
gptkb:CIFAR-100
Oxford Pets
|
|
gptkbp:is_optimized_for
|
gptkb:Adam
Mobile and Edge Devices
|
|
gptkbp:is_part_of
|
Open Source Projects
Computer Vision Libraries
Deep Learning Frameworks
AI Research Initiatives
Model Zoos
Efficient Net Architecture
|
|
gptkbp:is_popular_in
|
gptkb:Research_Institute
Industry Applications
|
|
gptkbp:is_standardized_by
|
gptkb:Batch_Normalization
|
|
gptkbp:is_used_for
|
Feature Extraction
Fine-tuning
|
|
gptkbp:is_used_in
|
Computer Vision Tasks
|
|
gptkbp:learns_move
|
gptkb:theorem
|
|
gptkbp:losses
|
Cross-Entropy Loss
|
|
gptkbp:orbital_period
|
5.3 million
|
|
gptkbp:performance
|
gptkb:Image_Net_Challenge
Model Efficiency
FLO Ps
CVPR Competitions
ICCV Competitions
Neur IPS Competitions
Top-1 accuracy of 77.1% on Image Net
|
|
gptkbp:predecessor
|
Baseline CN Ns
|
|
gptkbp:provides_information_on
|
gptkb:Image_Net
|
|
gptkbp:scales
|
Compound Scaling
|
|
gptkbp:speed
|
Faster inference than previous models
|
|
gptkbp:successor
|
Efficient Net family
|
|
gptkbp:supports
|
Multi-Label Classification
|
|
gptkbp:uses
|
Depthwise Separable Convolutions
|
|
gptkbp:bfsParent
|
gptkb:Efficient_Net
|
|
gptkbp:bfsLayer
|
5
|