From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Original author(s)Forrest Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, Bill Dally, Kurt Keutzer
Initial release22 February 2016; 3 years ago (2016-02-22)
Stable release
TypeDeep neural network
LicenseBSD license

SqueezeNet is the name of a deep neural network for computer vision that was released in 2016. SqueezeNet was developed by researchers at DeepScale, University of California, Berkeley, and Stanford University. In designing SqueezeNet, the authors' goal was to create a smaller neural network with fewer parameters that can more easily fit into computer memory and can more easily be transmitted over a computer network.[1]

Framework support for SqueezeNet[edit]

SqueezeNet was originally released on February 22, 2016.[2] 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.[3] On March 2, 2016, Guo Haria released a port of SqueezeNet for the Apache MXNet framework.[4] On June 3, 2016, Tammy Yang released a port of SqueezeNet for the Keras framework.[5] In 2017, companies including Baidu, Xilinx, Imagination Technologies, and Synopsys demonstrated SqueezeNet running on low-power processing platforms such as smartphones, FPGAs, and custom processors.[6][7][8][9]

As of 2018, SqueezeNet ships "natively" as part of the source code of a number of deep learning frameworks such as PyTorch, Apache MXNet, and Apple CoreML.[10][11][12] In addition, 3rd party developers have created implementations of SqueezeNet that are compatible with frameworks such as TensorFlow.[13] Below is a summary of frameworks that support SqueezeNet.

Framework SqueezeNet Support References
Apache MXNet Native [11]
Apple CoreML Native [12]
Caffe2 Native [14]
Keras 3rd party [5]
MATLAB Deep Learning Toolbox Native [15]
ONNX Native [16]
PyTorch Native [10]
TensorFlow 3rd party [13]
Wolfram Mathematica Native [17]

Relationship to AlexNet[edit]

SqueezeNet was originally described in a paper entitled "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size."[18] AlexNet is a deep neural network that has 240MB of parameters, and SqueezeNet has just 5MB of parameters. 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.[19] What SqueezeNet and AlexNet have in common is that both of them achieve approximately the same level of accuracy when evaluated on the ImageNet image classification validation dataset.

Relationship to Deep Compression[edit]

Model compression (e.g. quantization and pruning of model parameters) can be applied to a deep neural network after it has been trained.[20] 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 5MB to 500KB.[18] Deep Compression has also been applied to other DNNs such as AlexNet and VGG.[21]

Offshoots of SqueezeNet[edit]

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.

DNN Model Application Original




SqueezeDet[22][23] Object Detection

on Images

TensorFlow[24] Caffe[25], Keras[26][27][28]
SqueezeSeg[29] Semantic



SqueezeNext[31] Image


Caffe[32] TensorFlow[33], Keras[34],


SqueezeNAS[36][37] Neural Architecture Search

for Semantic Segmentation


In addition, the open-source research community has extended SqueezeNet to other applications, including semantic segmentation of images and style transfer.[39][40][41]


  1. ^ Ganesh, Abhinav. "Deep Learning Reading Group: SqueezeNet". KDnuggets. Retrieved 2018-04-07.
  2. ^ "SqueezeNet". GitHub. 2016-02-22. Retrieved 2018-05-12.
  3. ^ Bell, Eddie (2016-02-26). "An implementation of SqueezeNet in Chainer". GitHub. Retrieved 2018-05-12.
  4. ^ Haria, Guo (2016-03-02). "SqueezeNet for MXNet". GitHub. Retrieved 2018-05-12.
  5. ^ a b Yang, Tammy (2016-06-03). "SqueezeNet Keras Implemenation". GitHub. Retrieved 2018-05-12.
  6. ^ Chirgwin, Richard (2017-09-26). "Baidu puts open source deep learning into smartphones". The Register. Retrieved 2018-04-07.
  7. ^ Bush, Steve (2018-01-25). "Neural network SDK for PowerVR GPUs". Electronics Weekly. Retrieved 2018-04-07.
  8. ^ Yoshida, Junko (2017-03-13). "Xilinx AI Engine Steers New Course". EE Times. Retrieved 2018-05-13.
  9. ^ Boughton, Paul (2017-08-28). "Deep learning computer vision algorithms ported to processor IP". Engineer Live. Retrieved 2018-04-07.
  10. ^ a b "squeezenet.py". GitHub: PyTorch. Retrieved 2018-05-12.
  11. ^ a b "squeezenet.py". GitHub: Apache MXNet. Retrieved 2018-04-07.
  12. ^ a b "CoreML". Apple. Retrieved 2018-04-10.
  13. ^ a b Poster, Domenick. "Tensorflow implementation of SqueezeNet". GitHub. Retrieved 2018-05-12.
  14. ^ Inkawhich, Nathan. "SqueezeNet Model Quickload Tutorial". GitHub: Caffe2. Retrieved 2018-04-07.
  15. ^ "SqueezeNet for MATLAB Deep Learning Toolbox". Mathworks. Retrieved 2018-10-03.
  16. ^ Fang, Lu. "SqueezeNet for ONNX". Open Neural Network eXchange.
  17. ^ "SqueezeNet V1.1 Trained on ImageNet Competition Data". Wolfram Neural Net Repository. Retrieved 2018-05-12.
  18. ^ a b Iandola, Forrest N; Han, Song; Moskewicz, Matthew W; Ashraf, Khalid; Dally, William J; Keutzer, Kurt (2016). "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size". arXiv:1602.07360 [cs.CV].
  19. ^ "SqueezeNet". Short Science. Retrieved 2018-05-13.
  20. ^ Gude, Alex (2016-08-09). "Lab41 Reading Group: Deep Compression". Retrieved 2018-05-08.
  21. ^ Han, Song (2016-11-06). "Compressing and regularizing deep neural networks". O'Reilly. Retrieved 2018-05-08.
  22. ^ Wu, Bichen; Wan, Alvin; Iandola, Forrest; Jin, Peter H.; Keutzer, Kurt (2016). "SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving". arXiv:1612.01051 [cs.CV].
  23. ^ Nunes Fernandes, Edgar (2017-03-02). "Introducing SqueezeDet: low power fully convolutional neural network framework for autonomous driving". The Intelligence of Information. Retrieved 2019-03-31.
  24. ^ Wu, Bichen (2016-12-08). "SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving". GitHub. Retrieved 2018-12-26.
  25. ^ Kuan, Xu (2017-12-20). "Caffe SqueezeDet". GitHub. Retrieved 2018-12-26.
  26. ^ Padmanabha, Nischal (2017-03-20). "SqueezeDet on Keras". GitHub. Retrieved 2018-12-26.
  27. ^ Ehmann, Christopher (2018-05-29). "Fast object detection with SqueezeDet on Keras". Medium. Retrieved 2019-03-31.
  28. ^ Ehmann, Christopher (2018-05-02). "A deeper look into SqueezeDet on Keras". Medium. Retrieved 2019-03-31.
  29. ^ Wu, Bichen; Wan, Alvin; Yue, Xiangyu; Keutzer, Kurt (2017). "SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud". arXiv:1710.07368 [cs.CV].
  30. ^ Wu, Bichen (2017-12-06). "SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud". GitHub. Retrieved 2018-12-26.
  31. ^ Gholami, Amir; Kwon, Kiseok; Wu, Bichen; Tai, Zizheng; Yue, Xiangyu; Jin, Peter; Zhao, Sicheng; Keutzer, Kurt (2018). "SqueezeNext: Hardware-Aware Neural Network Design". arXiv:1803.10615 [cs.CV].
  32. ^ Gholami, Amir (2018-04-18). "SqueezeNext". GitHub. Retrieved 2018-12-29.
  33. ^ Verhulsdonck, Tijmen (2018-07-09). "SqueezeNext Tensorflow: A tensorflow Implementation of SqueezeNext". GitHub. Retrieved 2018-12-29.
  34. ^ Sémery, Oleg (2018-09-24). "SqueezeNext, implemented in Keras". Retrieved 2018-12-29.
  35. ^ Lu, Yi (2018-06-21). "SqueezeNext.PyTorch". GitHub. Retrieved 2018-12-29.
  36. ^ Shaw, Albert; Hunter, Daniel; Iandola, Forrest; Sidhu, Sammy (2019). "SqueezeNAS: Fast neural architecture search for faster semantic segmentation". arXiv:1908.01748 [cs.LG].
  37. ^ Yoshida, Junko (2019-08-25). "Does Your AI Chip Have Its Own DNN?". EE Times. Retrieved 2019-09-12.
  38. ^ Shaw, Albert (2019-08-27). "SqueezeNAS". GitHub. Retrieved 2019-09-12.
  39. ^ Treml, Michael; et al. (2016). "Speeding up Semantic Segmentation for Autonomous Driving". NIPS MLITS Workshop. Retrieved 2019-07-21.
  40. ^ Zeng, Li (2017-03-22). "SqueezeNet Neural Style on PyTorch". GitHub. Retrieved 2019-07-21.
  41. ^ Wu, Bichen; Keutzer, Kurt (2017). "The Impact of SqueezeNet" (PDF). UC Berkeley. Retrieved 2019-07-21.