Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio

Understand

Automatic designing computationally efficient neural networks has received much attention in recent years.

• Existing approaches either utilize network pruning or leverage the network architecture search methods.
• This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs, so that under each network configuration, one can estimate the FLOPs utilization ratio (FUR) for each layer and use it to determine whether to increase or decrease the number of channels on the layer.
• Note that FUR, like the gradient of a non-linear function, is accurate only in a small neighborhood of the current network.