mobilenetv2(width_mult, configs; inchannels = 3, max_width = 1280, nclasses = 1000)

Create a MobileNetv2 model. (reference).

Arguments

• width_mult: Controls the number of output feature maps in each block (with 1.0 being the default in the paper)

• configs: A “list of tuples” configuration for each layer that details:

  • t: The expansion factor that controls the number of feature maps in the bottleneck layer
  • c: The number of output feature maps
  • n: The number of times a block is repeated
  • s: The stride of the convolutional kernel
  • a: The activation function used in the bottleneck layer

• inchannels: The number of input channels. The default value is 3.

• max_width: The maximum number of feature maps in any layer of the network

• nclasses: The number of output classes