SqueezeNet

The SqueezeNet architecture

Smaller CNNs offer at least three advantages: less computation, less bandwidth and more feasible to deploy on FPGAs. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB.

  • Strategy 1. Replace 3x3 filters with 1x1 filters.
  • Strategy 2. Decrease the number of input channels to 3x3 filters.
  • Strategy 3. Downsample late in the network so that convolution layers have large activation maps.
SqueezeNet_第1张图片
Fire Module
SqueezeNet_第2张图片
Macroarchitectural view of our SqueezeNet architecture
SqueezeNet_第3张图片

Experiment

SqueezeNet_第4张图片

References:
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, 2017,arXiv: Computer Vision and Pattern Recognition

你可能感兴趣的:(SqueezeNet)