invertedresidualv3(inplanes, hidden_planes, outplanes, kernel_size, stride, use_se, use_hs)

Create a basic inverted residual block for MobileNetv3 (reference).

Arguments

• inplanes: The number of input feature maps
• hidden_planes: The number of feature maps in the hidden layer
• outplanes: The number of output feature maps
• kernel_size: The kernel size of the convolutional layers
• stride: The stride of the convolutional kernel, has to be either 1 or 2
• use_se: If true, Squeeze and Excitation layer will be used
• use_hs: If true, Hard-Swish activation function will be used