SqueezeNet

Use the mouse wheel or two fingers (on touchscreens) to zoom in and out of the map.

Export map as:

Research this topic

Explore the main themes, entities and connections around SqueezeNet. Start with the topic map, then use the sections below for research and deeper semantic analysis.

Explore this topic

Start with a few of the strongest sections from the source topic. These are research directions, not a list of keywords you must use.

Version history

Caffe Apache MXNet Keras Baidu Xilinx

12 related topics

Relationship to other networks

Model compression

1 related topics

Variants

Style transfer

1 related topics

Overview

Deep neural network Image classification DeepScale University of California, Berkeley Stanford University

7 related topics

Key facts & relationships

High-confidence facts extracted from structured source data. Use them as anchors for further research.

License: BSD license
Original authors: Forrest Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, Bill Dally, Kurt Keutzer
Release: 22 February 2016; 10 years ago (2016-02-22)
Repository: github.com/DeepScale/SqueezeNet
Stable release: v1.1 (June 6, 2016; 10 years ago (2016-06-06))
Type: Deep neural network

Topics to explore

Browse the full topic structure. Each item opens a new analysis centered on that subject.

Overview

Version history

Relationship to other networks

Model compression

Variants

Style transfer Neural Style Transfer

Advanced semantic analysis

Deeper signals for content research, entity SEO and topical coverage. The plain-language headings explain what each technical view is useful for.

Map overview Semantic statistics

Nodes26

Edges25

Triples57

Avg. degree1.92

Density0.076923

Components1

How this topic connects Entity context

See the strongest relationship patterns around the current topic before diving into the raw triples.

SqueezeNet

Top relations

related to history · 24

SqueezeNet → Apache MXNet, Apple CoreML, As, Baidu, Below, Caffe, Chainer, Eddie Bell, February, FPGAs, Guo Haria, Imagination Technologies, In, Keras, On February, On June, On March, PyTorch, Shortly, Synopsys

related to AlexNet · 9

SqueezeNet → AlexNet, AlexNet-level, DNN, However, ImageNet, MB, Rather, This, What SqueezeNet

related to Model compression · 8

SqueezeNet → AlexNet, Deep Compression, DNNs, In, KB, MB, Model, VGG

related to Variants · 3

SqueezeNet → As, In, Some

is a · 2

SqueezeNet → deep neural network for image classification released in 2016, entirely different DNN architecture than AlexNet

License · 1

SqueezeNet → BSD license

Original authors · 1

SqueezeNet → Forrest Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, Bill Dally, Kurt Keutzer

Release · 1

SqueezeNet → 22 February 2016; 10 years ago (2016-02-22)

Repository · 1

SqueezeNet → github.com/DeepScale/SqueezeNet

Stable release · 1

SqueezeNet → v1.1 (June 6, 2016; 10 years ago (2016-06-06))

Important terminology Word statistics

Use these terms to understand the vocabulary surrounding the topic, not as a checklist for keyword stuffing.

Important terminology

deep model neural network alexnet released 2016 accuracy learning frameworks parameters size classification compression original framework deepscale version imagenet open-source

Entity relationships Subject–Predicate–Object triples

Subject	Predicate	Object	Confidence	Src
SqueezeNet	License	BSD license	1.00	infobox
SqueezeNet	Original authors	Forrest Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, Bill Dally, Kurt Keutzer	1.00	infobox
SqueezeNet	Release	22 February 2016; 10 years ago (2016-02-22)	1.00	infobox
SqueezeNet	Repository	github.com/DeepScale/SqueezeNet	1.00	infobox
SqueezeNet	Stable release	v1.1 (June 6, 2016; 10 years ago (2016-06-06))	1.00	infobox
SqueezeNet	Type	Deep neural network	1.00	infobox
SqueezeNet	is a	deep neural network for image classification released in 2016	0.90	text
SqueezeNet	is a	entirely different DNN architecture than AlexNet	0.90	text
smartphones	instance of	and Synopsys demonstrated SqueezeNet running on low-power processing platforms	0.80	text
FPGAs	instance of	and Synopsys demonstrated SqueezeNet running on low-power processing platforms	0.80	text
and custom processors.As of 2018	instance of	and Synopsys demonstrated SqueezeNet running on low-power processing platforms	0.80	text
SqueezeNet ships	instance of	and Synopsys demonstrated SqueezeNet running on low-power processing platforms	0.80	text

Related concept clusters Concept neighborhoods

These clusters group vocabulary that occurs around closely connected concepts in the source material.

Connections between topic areas Semantic bridges

Bridges can reveal useful research angles that are easy to miss in a flat list of related terms.

Min side: 3