Category: 02. Layers API

Usage of constraints Classes from the keras.constraints module allow setting constraints (eg. non-negativity) on model parameters during training. They are per-variable projection functions applied to the target variable after each gradient update (when using fit()). The exact API will depend on the layer, but the layers Dense, Conv1D, Conv2D and Conv3D have a unified API. These layers expose two keyword arguments: Available weight constraints…

Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes. Regularization penalties are applied on a per-layer basis. The exact API will depend on the layer, but many layers (e.g. Dense, Conv1D, Conv2D and Conv3D) have a unified API. These layers expose 3 keyword…

Usage of initializers Initializers define the way to set the initial random weights of Keras layers. The keyword arguments used for passing initializers to layers depends on the layer. Usually, it is simply kernel_initializer and bias_initializer: All built-in initializers can also be passed via their string identifier: Available initializers The following built-in initializers are available as part of…

Usage of activations Activations can either be used through an Activation layer, or through the activation argument supported by all forward layers: This is equivalent to: All built-in activations may also be passed via their string identifier: Available activations relu function Applies the rectified linear unit activation function. With default values, this returns the standard ReLU activation: max(x, 0), the element-wise…

This is the class from which all layers inherit. A layer is a callable object that takes as input one or more tensors and that outputs one or more tensors. It involves computation, defined in the call() method, and a state (weight variables). State can be created: Layers are recursively composable: If you assign a Layer instance as an attribute…