|
gptkbp:instance_of
|
gptkb:microprocessor
gptkb:television_channel
|
|
gptkbp:bfsLayer
|
4
|
|
gptkbp:bfsParent
|
gptkb:Mobile_Net
|
|
gptkbp:application
|
Image Classification
Object Detection
Semantic Segmentation
|
|
gptkbp:architectural_style
|
gptkb:television_channel
Lightweight Model
|
|
gptkbp:community_support
|
Active Community
|
|
gptkbp:developed_by
|
gptkb:Job_Search_Engine
gptkb:Neural_Architecture_Search
|
|
gptkbp:established
|
Swish
Re LU
|
|
gptkbp:features
|
Low Latency
High Speed
High Accuracy
Lightweight Design
Efficient Architecture
|
|
gptkbp:has_achievements
|
High Accuracy on Mobile Devices
|
|
gptkbp:has_variants
|
gptkb:Mobile_Net_V3-Large
gptkb:Mobile_Net_V3-Small
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Mobile Net V3
|
|
gptkbp:improves
|
gptkb:Mobile_Net_V2
|
|
gptkbp:input_output
|
128x128
224x224
160x160
192x192
|
|
gptkbp:is_a_framework_for
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_adopted_by
|
Industry Applications
|
|
gptkbp:is_available_in
|
Pre-trained Models
|
|
gptkbp:is_compatible_with
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_considered
|
gptkb:Cloud_Computing_Service
gptkb:technology
Io T Devices
|
|
gptkbp:is_designed_for
|
gptkb:software_framework
Real-time Applications
Edge Devices
Mobile Vision Applications
|
|
gptkbp:is_designed_to
|
Enhance Inference Speed
Maintain High Accuracy
Reduce Model Size
|
|
gptkbp:is_documented_in
|
Research Papers
|
|
gptkbp:is_evaluated_by
|
gptkb:Image_Net_Dataset
Memory Usage
Real-time Processing
Robustness
Generalization
Resource Efficiency
Inference Time
Speed and Accuracy
FLO Ps
Mobile Device Constraints
|
|
gptkbp:is_influenced_by
|
gptkb:Mobile_Net_V1
gptkb:Mobile_Net_V2
|
|
gptkbp:is_optimized_for
|
gptkb:smartphone
gptkb:Adam
Low Latency
Performance and Efficiency
SGD
|
|
gptkbp:is_part_of
|
gptkb:Mobile_Net_Family
Computer Vision Research
|
|
gptkbp:is_supported_by
|
Community Contributions
|
|
gptkbp:is_used_for
|
gptkb:streaming_service
Feature Extraction
|
|
gptkbp:is_used_in
|
gptkb:Autonomous_Vehicles
gptkb:software
Real-time Applications
Retail Analytics
Healthcare Imaging
Smart Cameras
|
|
gptkbp:latest_version
|
gptkb:Mobile_Net_V3-Large
gptkb:Mobile_Net_V3-Small
|
|
gptkbp:losses
|
Cross-Entropy Loss
|
|
gptkbp:orbital_period
|
5.4 million
|
|
gptkbp:performance
|
gptkb:Efficient_Net
gptkb:Res_Net
gptkb:Mobile_Net_V2
Top-1 Accuracy
Top-5 Accuracy
|
|
gptkbp:predecessor
|
gptkb:Mobile_Net_V4
|
|
gptkbp:provides_information_on
|
gptkb:Image_Net
|
|
gptkbp:publishes
|
Mobile Net V3: A Lightweight Neural Network for Mobile Vision Applications
|
|
gptkbp:related_model
|
Small
|
|
gptkbp:release_year
|
gptkb:2019
|
|
gptkbp:released_in
|
gptkb:2020
|
|
gptkbp:repository
|
gptkb:archive
|
|
gptkbp:resolution
|
1000 classes
|
|
gptkbp:successor
|
gptkb:Mobile_Net_V2
|
|
gptkbp:supports
|
gptkb:streaming_service
Image Classification
Object Detection
Fine-tuning
Semantic Segmentation
|
|
gptkbp:training
|
gptkb:streaming_service
gptkb:Varies
Supervised Learning
Large Scale Datasets
|
|
gptkbp:use_case
|
gptkb:Autonomous_Vehicles
gptkb:software
gptkb:robot
Mobile Applications
Io T Devices
|
|
gptkbp:uses
|
Depthwise Separable Convolutions
Squeeze-and-Excitation Blocks
Linear Bottlenecks
|
|
gptkbp:utilizes
|
Squeeze-and-Excitation Blocks
|