Expand 3D CNN

Definition

Expand 3D CNN (X3D) model tried to find the optimal parameters for 3D Residual Networks using AutoML method. It tunes six parameters:

• X-Fast (${\gamma }_{\tau }$): the input frame rate (temporal resolution)
• X-Temporal (${\gamma }_t$): the number of frames in the input
• X-Spatial (${\gamma }_s$): the spacial resolution
• X-Depth (${\gamma }_d$): the depth of the network
• X-Width (${\gamma }_w$): the number of channels for all layers
• X-Bottleneck (${\gamma }_b$): the inner channel width of the center convolutional filter in each residual block