Dropout(p; dims=:, rng = default_rng_value())

Dropout layer.

While training, for each input, this layer either sets that input to 0 (with probability p) or scales it by 1 / (1 - p). To apply dropout along certain dimension(s), specify the dims keyword. e.g. Dropout(p; dims = 3) will randomly zero out entire channels on WHCN input (also called 2D dropout). This is used as a regularisation, i.e. it reduces overfitting during training.

In the forward pass, this layer applies the Flux.dropout function. See that for more details.

Specify rng to use a custom RNG instead of the default. Custom RNGs are only supported on the CPU.

Does nothing to the input once Flux.testmode! is true.

Examples

			julia> m = Chain(Dense(1 => 1), Dropout(1));

julia> Flux.trainmode!(m);

julia> y = m([1]);

julia> y == [0]
true

julia> m = Chain(Dense(1000 => 1000), Dropout(0.5));

julia> Flux.trainmode!(m);

julia> y = m(ones(1000));

julia> isapprox(count(==(0), y) / length(y), 0.5, atol=0.1)
true