Section Navigation
Attention module from [Lee2019].
in_channels (int) – number of input feature channels
use_mlp (bool, default=False) – whether to use fully-connected layers instead of a convolutional layer,
reduction_rate (int, default=4) – reduction ratio of the fully-connected layers (if used),
References
Lee, H., Kim, H., Nam, H., 2019. SRM: A Style-based
Recalibration Module for Convolutional Neural Networks. ICCV 2019.
Methods
Apply the Style-based Recalibration Module to the input tensor.
x (Pytorch.Tensor)
Pytorch.Tensor
SRM
SRM.forward()