speechbrain.nnet.dropout module

Library implementing dropout.

Authors

• Mirco Ravanelli 2020

Summary

Classes:

Dropout2d

This function implements dropout 2d.

Reference

class speechbrain.nnet.dropout.Dropout2d(drop_rate, inplace=False)

Bases: Module

This function implements dropout 2d. It randomly put zeros on entire channels.

Parameters:

• dropout_rate (float) – It is the dropout factor (between 0 and 1).

• inplace (bool) – If True, it uses inplace operations.

Example

>>> drop = Dropout2d(drop_rate=0.5)
>>> inputs = torch.rand(10, 50, 40)
>>> output=drop(inputs)
>>> output.shape
torch.Size([10, 50, 40])

forward(x)

Applies dropout 2d to the input tensor.

Parameters:

x (torch.Tensor (batch, time, channel1, channel2)) – input to normalize. 4d tensors are expected.