SqueezeNet is a

deep neural network Deep learning is a subset of machine learning that focuses on utilizing multilayered neural network (machine learning), neural networks to perform tasks such as Statistical classification, classification, Regression analysis, regression, and re ...

for

image classification Computer vision tasks include methods for acquiring, processing, analyzing, and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the form o ...

released in 2016. SqueezeNet was developed by researchers at DeepScale,

University of California, Berkeley The University of California, Berkeley (UC Berkeley, Berkeley, Cal, or California), is a Public university, public Land-grant university, land-grant research university in Berkeley, California, United States. Founded in 1868 and named after t ...

, and

Stanford University Leland Stanford Junior University, commonly referred to as Stanford University, is a Private university, private research university in Stanford, California, United States. It was founded in 1885 by railroad magnate Leland Stanford (the eighth ...

. In designing SqueezeNet, the authors' goal was to create a smaller neural network with fewer parameters while achieving competitive accuracy. Their best-performing model achieved the same accuracy as

AlexNet AlexNet is a convolutional neural network architecture developed for image classification tasks, notably achieving prominence through its performance in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC). It classifies images into 1, ...

ImageNet The ImageNet project is a large visual database designed for use in Outline of object recognition, visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictur ...

classification, but has a size 510x less than it.

Version history

SqueezeNet was originally released on February 22, 2016. This original version of SqueezeNet was implemented on top of the Caffe deep learning software framework. Shortly thereafter, the open-source research community ported SqueezeNet to a number of other deep learning frameworks. On February 26, 2016, Eddie Bell released a port of SqueezeNet for the Chainer deep learning framework. On March 2, 2016, Guo Haria released a port of SqueezeNet for the Apache MXNet framework. On June 3, 2016, Tammy Yang released a port of SqueezeNet for the

Keras Keras is an open-source library that provides a Python interface for artificial neural networks. Keras was first independent software, then integrated into the TensorFlow library, and later added support for more. "Keras 3 is a full rewrite o ...

framework. In 2017, companies including

Baidu Baidu, Inc. ( ; ) is a Chinese multinational technology company specializing in Internet services and artificial intelligence. It holds a dominant position in China's search engine market (via Baidu Search), and provides a wide variety of o ...

Xilinx Xilinx, Inc. ( ) was an American technology and semiconductor company that primarily supplied programmable logic devices. The company is renowned for inventing the first commercially viable field-programmable gate array (FPGA). It also pioneered ...

Imagination Technologies Imagination Technologies Group Limited is a British semiconductor and Computer software, software design company owned by Canyon Bridge Capital Partners, a private equity fund based in Beijing that is ultimately owned by the Chinese government. ...

, and

Synopsys Synopsys, Inc. is an American electronic design automation (EDA) company headquartered in Sunnyvale, California, that focuses on silicon design and verification, silicon intellectual property and software security and quality. Synopsys sup ...

demonstrated SqueezeNet running on low-power processing platforms such as

smartphone A smartphone is a mobile phone with advanced computing capabilities. It typically has a touchscreen interface, allowing users to access a wide range of applications and services, such as web browsing, email, and social media, as well as multi ...

FPGA A field-programmable gate array (FPGA) is a type of configurable integrated circuit that can be repeatedly programmed after manufacturing. FPGAs are a subset of logic devices referred to as programmable logic devices (PLDs). They consist of a ...

s, and custom processors. As of 2018, SqueezeNet ships "natively" as part of the source code of a number of deep learning frameworks such as

PyTorch PyTorch is a machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, originally developed by Meta AI and now part of the Linux Foundation umbrella. It is one of the mo ...

, Apache MXNet, and

Apple An apple is a round, edible fruit produced by an apple tree (''Malus'' spp.). Fruit trees of the orchard or domestic apple (''Malus domestica''), the most widely grown in the genus, are agriculture, cultivated worldwide. The tree originated ...

CoreML. In addition, third party developers have created implementations of SqueezeNet that are compatible with frameworks such as

TensorFlow TensorFlow is a Library (computing), software library for machine learning and artificial intelligence. It can be used across a range of tasks, but is used mainly for Types of artificial neural networks#Training, training and Statistical infer ...

. Below is a summary of frameworks that support SqueezeNet.

Relationship to other networks

AlexNet

SqueezeNet was originally described in ''SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size''.

is a deep neural network that has 240 MB of parameters, and SqueezeNet has just 5 MB of parameters. This small model size can more easily fit into computer memory and can more easily be transmitted over a computer network. However, it's important to note that SqueezeNet is not a "squeezed version of AlexNet." Rather, SqueezeNet is an entirely different DNN architecture than AlexNet. What SqueezeNet and AlexNet have in common is that both of them achieve approximately the same level of accuracy when evaluated on the

image classification validation dataset.

Model compression

Model compression (e.g. quantization and pruning of model parameters) can be applied to a deep neural network after it has been trained. In the SqueezeNet paper, the authors demonstrated that a model compression technique called Deep Compression can be applied to SqueezeNet to further reduce the size of the parameter file from 5 MB to 500 KB. Deep Compression has also been applied to other DNNs, such as AlexNet and VGG.

Variants

Some of the members of the original SqueezeNet team have continued to develop resource-efficient deep neural networks for a variety of applications. A few of these works are noted in the following table. As with the original SqueezeNet model, the open-source research community has ported and adapted these newer "squeeze"-family models for compatibility with multiple deep learning frameworks. In addition, the open-source research community has extended SqueezeNet to other applications, including semantic segmentation of images and style transfer.

References