tf.compat.v1.layers.dense

Functional interface for the densely-connected layer.

tf.compat.v1.layers.dense(
    inputs, units, activation=None, use_bias=True, kernel_initializer=None,
    bias_initializer=tf.compat.v1.zeros_initializer(), kernel_regularizer=None,
    bias_regularizer=None, activity_regularizer=None, kernel_constraint=None,
    bias_constraint=None, trainable=True, name=None, reuse=None
)

Migrate to TF2

This API is not compatible with eager execution or tf.function.

Please refer to tf.layers section of the migration guide to migrate a TensorFlow v1 model to Keras. The corresponding TensorFlow v2 layer is tf.keras.layers.Dense.

Structural Mapping to Native TF2

None of the supported arguments have changed name.

Before:

 y = tf.compat.v1.layers.dense(x, units=3)

After:

To migrate code using TF1 functional layers use the Keras Functional API:

 x = tf.keras.Input((28,))
 y = tf.keras.layers.Dense(units=3)(x)
 model = tf.keras.Model(x, y)

Description

This layer implements the operation: outputs = activation(inputs * kernel + bias) where activation is the activation function passed as the activation argument (if not None), kernel is a weights matrix created by the layer, and bias is a bias vector created by the layer (only if use_bias is True).

inputs Tensor input.
units Integer or Long, dimensionality of the output space.
activation Activation function (callable). Set it to None to maintain a linear activation.
use_bias Boolean, whether the layer uses a bias.
kernel_initializer Initializer function for the weight matrix. If None (default), weights are initialized using the default initializer used by tf.compat.v1.get_variable.
bias_initializer Initializer function for the bias.
kernel_regularizer Regularizer function for the weight matrix.
bias_regularizer Regularizer function for the bias.
activity_regularizer Regularizer function for the output.
kernel_constraint An optional projection function to be applied to the kernel after being updated by an Optimizer (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training.
bias_constraint An optional projection function to be applied to the bias after being updated by an Optimizer.
trainable Boolean, if True also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
name String, the name of the layer.
reuse Boolean, whether to reuse the weights of a previous layer by the same name.

Output tensor the same shape as inputs except the last dimension is of size units.

ValueError if eager execution is enabled.