Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

Understand

Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a computational budget.

• However, such a pruning policy often leads to excessive reduction of that dimension, thus inducing a huge accuracy loss.
• To alleviate this issue, we argue that pruning should be conducted along three dimensions comprehensively.
• For this purpose, our pruning framework formulates pruning as an optimization problem.