Professional Documents
Culture Documents
Squeezenet Presentation
Squeezenet Presentation
What we what?
1. Reduce number of parameters and model size.
2. Maintain same accuracy level with AlexNet.
Benefits
1. Small Models train faster.
2. Less overhead when exporting new models to clients.
3. Feasible FPGA and embedded deployment.
2
SqueezeNet Architectural Design Strategy
3
Fire Module
Image Source
4
SqueezeNet Architectural Dimensions
Image Source
5
Some Intuitions
6
Results
Image Source
7
Deep Compression
8
Other Architectures with Bypass
9
10