Keras 3 API documentation
Models API Layers API The base Layer class Layer activations Layer weight initializers Layer weight regularizers Layer weight constraints Core layers Convolution layers Pooling layers Recurrent layers Preprocessing layers Normalization layers Regularization layers Attention layers Reshaping layers Merging layers Activation layers Backend-specific layers Callbacks API Ops API Optimizers Metrics Losses Data loading Built-in small datasets Keras Applications Mixed precision Multi-device distribution RNG API Quantizers Scope Rematerialization Utilities
Keras 2 API documentation
► Keras 3 API documentation / Layers API / Activation layers / ReLU layer

ReLU layer

[source]

ReLU class

keras.layers.ReLU(max_value=None, negative_slope=0.0, threshold=0.0, **kwargs)

Rectified Linear Unit activation function layer.

Formula:

f(x) = max(x,0) f(x) = max_value if x >= max_value f(x) = x if threshold <= x < max_value f(x) = negative_slope * (x - threshold) otherwise

Example

relu_layer = keras.layers.ReLU( max_value=10, negative_slope=0.5, threshold=0, ) input = np.array([-10, -5, 0.0, 5, 10]) result = relu_layer(input) # result = [-5. , -2.5, 0. , 5. , 10.]

Arguments

  • max_value: Float >= 0. Maximum activation value. None means unlimited. Defaults to None.
  • negative_slope: Float >= 0. Negative slope coefficient. Defaults to 0.0.
  • threshold: Float >= 0. Threshold value for thresholded activation. Defaults to 0.0.
  • **kwargs: Base layer keyword arguments, such as name and dtype.
ReLU layer
ReLU class