LeakyReLU layer

• 원본 링크 : https://keras.io/api/layers/activation_layers/leaky_relu/
• 최종 확인 : 2024-11-25

source

LeakyReLU class

keras.layers.LeakyReLU(negative_slope=0.3, **kwargs)

Leaky version of a Rectified Linear Unit activation layer.

This layer allows a small gradient when the unit is not active.

Formula:

f(x) = alpha * x if x < 0
f(x) = x if x >= 0

Example

leaky_relu_layer = LeakyReLU(negative_slope=0.5)
input = np.array([-10, -5, 0.0, 5, 10])
result = leaky_relu_layer(input)

Arguments

• negative_slope: Float >= 0.0. Negative slope coefficient. Defaults to 0.3.
• **kwargs: Base layer keyword arguments, such as name and dtype.