tf.keras.experimental.LinearModel

TensorFlow 1 version View source on GitHub

Linear Model for regression and classification problems.

Inherits From: Model

tf.keras.experimental.LinearModel(
    units=1, activation=None, use_bias=True, kernel_initializer='zeros',
    bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None,
    **kwargs
)

This model approximates the following function:

$$y = \beta + \sum_{i=1}^{N} w_{i} * x_{i}$$

where

$$\beta$$

is the bias and

$$w_{i}$$

is the weight for each feature.

Example:

model = LinearModel()
model.compile(optimizer='sgd', loss='mse')
model.fit(x, y, epochs=epochs)

This model accepts sparse float inputs as well:

Example:

model = LinearModel()
opt = tf.keras.optimizers.Adam()
loss_fn = tf.keras.losses.MeanSquaredError()
with tf.GradientTape() as tape:
  output = model(sparse_input)
  loss = tf.reduce_mean(loss_fn(target, output))
grads = tape.gradient(loss, model.weights)
opt.apply_gradients(zip(grads, model.weights))

units Positive integer, output dimension without the batch size.
activation Activation function to use. If you don't specify anything, no activation is applied.
use_bias whether to calculate the bias/intercept for this model. If set to False, no bias/intercept will be used in calculations, e.g., the data is already centered.
kernel_initializer Initializer for the kernel weights matrices.
bias_initializer Initializer for the bias vector.
kernel_regularizer regularizer for kernel vectors.
bias_regularizer regularizer for bias vector.
**kwargs The keyword arguments that are passed on to BaseLayer.init.

distribute_strategy The tf.distribute.Strategy this model was created under.
layers

metrics_names Returns the model's display labels for all outputs.

inputs = tf.keras.layers.Input(shape=(3,))
outputs = tf.keras.layers.Dense(2)(inputs)
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer="Adam", loss="mse", metrics=["mae"])
model.metrics_names
[]

x = np.random.random((2, 3))
y = np.random.randint(0, 2, (2, 2))
model.fit(x, y)
model.metrics_names
['loss', 'mae']

inputs = tf.keras.layers.Input(shape=(3,))
d = tf.keras.layers.Dense(2, name='out')
output_1 = d(inputs)
output_2 = d(inputs)
model = tf.keras.models.Model(
   inputs=inputs, outputs=[output_1, output_2])
model.compile(optimizer="Adam", loss="mse", metrics=["mae", "acc"])
model.fit(x, (y, y))
model.metrics_names
['loss', 'out_loss', 'out_1_loss', 'out_mae', 'out_acc', 'out_1_mae',
'out_1_acc']

run_eagerly Settable attribute indicating whether the model should run eagerly.

Running eagerly means that your model will be run step by step, like Python code. Your model might run slower, but it should become easier for you to debug it by stepping into individual layer calls.

By default, we will attempt to compile your model to a static graph to deliver the best execution performance.

Methods

compile

View source

compile(
    optimizer='rmsprop', loss=None, metrics=None, loss_weights=None,
    weighted_metrics=None, run_eagerly=None, **kwargs
)

Configures the model for training.

Arguments
optimizer String (name of optimizer) or optimizer instance. See tf.keras.optimizers.
loss String (name of objective function), objective function or tf.keras.losses.Loss instance. See tf.keras.losses. An objective function is any callable with the signature loss = fn(y_true, y_pred), where y_true = ground truth values with shape = [batch_size, d0, .. dN], except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]. y_pred = predicted values with shape = [batch_size, d0, .. dN]. It returns a weighted loss float tensor. If a custom Loss instance is used and reduction is set to NONE, return value has the shape [batch_size, d0, .. dN-1] ie. per-sample or per-timestep loss values; otherwise, it is a scalar. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of losses. The loss value that will be minimized by the model will then be the sum of all individual losses.
metrics List of metrics to be evaluated by the model during training and testing. Each of this can be a string (name of a built-in function), function or a tf.keras.metrics.