|
gptkbp:instance_of
|
gptkb:television_channel
|
|
gptkbp:bfsLayer
|
6
|
|
gptkbp:bfsParent
|
gptkb:Squeeze_Net
|
|
gptkbp:architectural_style
|
Lightweight Model
|
|
gptkbp:based_on
|
Alex Net architecture
|
|
gptkbp:developed_by
|
gptkb:Deep_Scale
|
|
gptkbp:established
|
Re LU
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Squeeze Net 1.1
|
|
gptkbp:is_compatible_with
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_designed_for
|
Mobile and embedded vision applications
|
|
gptkbp:is_evaluated_by
|
gptkb:CIFAR-10
gptkb:Pascal_VOC
gptkb:COCO_dataset
gptkb:CIFAR-100
Action recognition tasks
Face recognition tasks
Gesture recognition tasks
Scene recognition tasks
|
|
gptkbp:is_implemented_in
|
gptkb:Keras
MX Net
|
|
gptkbp:is_known_for
|
Energy efficiency
Low latency
Real-time performance
High accuracy with fewer parameters
|
|
gptkbp:is_optimized_for
|
Low memory usage
|
|
gptkbp:is_part_of
|
gptkb:Squeeze_Net_family
|
|
gptkbp:is_used_in
|
gptkb:robot
gptkb:computer
gptkb:helicopter
Autonomous vehicles
Industrial automation
Mobile apps
Security surveillance
Augmented reality applications
Virtual reality applications
Wearable devices
Traffic monitoring
Healthcare applications
Agricultural monitoring
Smart cameras
Real-time image classification
Augmented reality glasses
Object detection tasks
Image segmentation tasks
|
|
gptkbp:orbital_period
|
1.24 million
|
|
gptkbp:performance
|
Model compression techniques
Top-5 accuracy of 57.5% on Image Net
|
|
gptkbp:predecessor
|
gptkb:Squeeze_Net_1.0
|
|
gptkbp:release_date
|
gptkb:2016
|
|
gptkbp:successor
|
gptkb:Squeeze_Net_1.2
|
|
gptkbp:supports
|
gptkb:streaming_service
|
|
gptkbp:training
|
gptkb:Image_Net_dataset
|
|
gptkbp:uses
|
Global Average Pooling
Fire modules
|
|
gptkbp:written_in
|
gptkb:Library
|