depthwise_sep_conv_bn(kernelsize, inplanes, outplanes, activation = relu;
                      rev = false,
                      stride = 1, pad = 0, dilation = 1, [bias, weight, init],
                      initβ = Flux.zeros32, initγ = Flux.ones32,
                      ϵ = 1f-5, momentum = 1f-1)

Create a depthwise separable convolution chain as used in MobileNet v1. This is sequence of layers:

• a kernelsize depthwise convolution from inplanes => inplanes
• a batch norm layer + activation
• a kernelsize convolution from inplanes => outplanes
• a batch norm layer + activation

See Fig. 3 in reference.

Arguments

• kernelsize: size of the convolution kernel (tuple)
• inplanes: number of input feature maps
• outplanes: number of output feature maps
• activation: the activation function for the final layer
• rev: set to true to place the batch norm before the convolution
• stride: stride of the first convolution kernel
• pad: padding of the first convolution kernel
• dilation: dilation of the first convolution kernel
• bias, weight, init: initialization for the convolution kernel (see Flux.Conv)
• initβ, initγ: initialization for the batch norm (see Flux.BatchNorm)
• ϵ, momentum: batch norm parameters (see Flux.BatchNorm)