conv_dw

plugins.extract.detect.retinaface.conv_dw(in_channels: int, out_channels: int, stride: int, leaky=0.1) → Sequential

Generates a double Conv Batch Norm sequential module for RetinaFace

Parameters:

• in_channels (int) – The number of input channels

• out_channels (int) – The number of output channels

• stride (int) – The number of strides. Default: 1

• leaky – The negative float value for the LeakyReLU. Default: 0.0

Return type:

The built sequential module