chainer.functions.dropout

chainer.functions.dropout(x, ratio=.5)[source]

Drops elements of input variable randomly.

This function drops input elements randomly with probability ratio and scales the remaining elements by factor 1 / (1 - ratio). In testing mode, it does nothing and just returns x.

Warning

train argument is not supported anymore since v2. Instead, use chainer.using_config('train', boolean). See chainer.using_config().

Parameters:
  • x (Variable) – Input variable.
  • ratio (float) – Dropout ratio. The ratio must be
  • <= ratio < 1.0. (0.0) –
Returns:

Output variable.

Return type:

Variable

See the paper by G. Hinton: Improving neural networks by preventing co-adaptation of feature detectors.