ML Paper Challenge Day 34, 35 — SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Papers with Code - SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model…

Day 34–35: 2020.05.15–16
Paper: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Category: Model/Optimization

SqueezeNet

Strategy

1. Replace 3x3 filters with 1x1 filters
2. Decrease the number of input channels to 3x3 filters using squeeze layers
3. Downsample late in the network so that convolution layers have large activation maps

Fire Module, comprised of

• a squeeze convolution layer (which has only 1x1 filters) (as per Strategy 1)
• feeding into an expand layer that has a mix of 1x1 and 3x3 convolution filters
• We expose three tunable dimensions (hyperparameters) in a Fire module: s\_(1x1)…