Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tfl.layers.PWLCalibration

View source on GitHub

Piecewise linear calibration layer.

tfl.layers.PWLCalibration(
    input_keypoints, units=1, output_min=None, output_max=None, clamp_min=False,
    clamp_max=False, monotonicity='none', convexity='none', is_cyclic=False,
    kernel_initializer='equal_heights', kernel_regularizer=None,
    impute_missing=False, missing_input_value=None, missing_output_value=None,
    num_projection_iterations=8, **kwargs
)

Used in the notebooks

Used in the tutorials

Layer takes input of shape (batch_size, units) or (batch_size, 1) and transforms it using units number of piecewise linear functions following monotonicity, convexity and bounds constraints if specified. If multi dimensional input is provides, each output will be for the corresponding input, otherwise all PWL functions will act on the same input. All units share the same layer configuration, but each has their separate set of trained parameters.

See tfl.layers.ParallelCombination layer for using PWLCalibration layer within Sequential Keras models.

Input shape:

Single input should be a rank-2 tensor with shape: (batch_size, units) or (batch_size, 1). The input can also be a list of two tensors of the same shape where the first tensor is the regular input tensor and the second is the is_missing tensor. In the is_missing tensor, 1.0 represents missing input and 0.0 represents available input.

Output shape:

Rank-2 tensor with shape: (batch_size, units).

Args:

  • input_keypoints: Ordered list of keypoints of piecewise linear function. Can be anything accepted by tf.convert_to_tensor().
  • units: Output dimension of the layer. See class comments for details.
  • output_min: Minimum output of calibrator.
  • output_max: Maximum output of calibrator.
  • clamp_min: For monotonic calibrators ensures that output_min is reached.
  • clamp_max: For monotonic calibrators ensures that output_max is reached.
  • monotonicity: Constraints piecewise linear function to be monotonic using 'increasing' or 1 to indicate increasing monotonicity, 'decreasing' or -1 to indicate decreasing monotonicity and 'none' or 0 to indicate no monotonicity constraints.
  • convexity: Constraints piecewise linear function to be convex or concave. Convexity is indicated by 'convex' or 1, concavity is indicated by 'concave' or -1, 'none' or 0 indicates no convexity/concavity constraints. Concavity together with increasing monotonicity as well as convexity together with decreasing monotonicity results in diminishing return constraints. Consider increasing the value of num_projection_iterations if convexity is specified, especially with larger number of keypoints.
  • is_cyclic: Whether the output for last keypoint should be identical to output for first keypoint. This is useful for features such as "time of day" or "degree of turn". If inputs are discrete and exactly match keypoints then is_cyclic will have an effect only if TFL regularizers are being used.
  • kernel_initializer: None or one of:
    • String "equal_heights": For pieces of pwl function to have equal heights.
    • String "equal_slopes": For pieces of pwl function to have equal slopes.
    • Any Keras initializer object. If you are passing such object make sure that you know how layer stores its data.
  • kernel_regularizer: None or single element or list of following:
    • Tuple ("laplacian", l1, l2) where l1 and l2 are floats which represent corresponding regularization amount for Laplacian regularizer. It penalizes the first derivative to make the function more constant. See tfl.pwl_calibration.LaplacianRegularizer for more details.
    • Tuple ("hessian", l1, l2) where l1 and l2 are floats which represent corresponding regularization amount for Hessian regularizer. It penalizes the second derivative to make the function more linear. See tfl.pwl_calibration.HessianRegularizer for more details.
    • Tuple ("wrinkle", l1, l2) where l1 and l2 are floats which represent corresponding regularization amount for wrinkle regularizer. It penalizes the third derivative to make the function more smooth. See 'tfl.pwl_calibration.WrinkleRegularizer` for more details.
    • Any Keras regularizer object.
  • impute_missing: Whether to learn an output for cases where input data is missing. If set to True, either missing_input_value should be initialized, or the call() method should get pair of tensors. See class input shape description for more details.
  • missing_input_value: If set, all inputs which are equal to this value will be considered as missing. Can not be set if impute_missing is False.
  • missing_output_value: If set, instead of learning output for missing inputs, simply maps them into this value. Can not be set if impute_missing is False.
  • num_projection_iterations: Number of iterations of the Dykstra's projection algorithm. Constraints are strictly satisfied at the end of each update, but the update will be closer to a true L2 projection with higher number of iterations. See tfl.pwl_calibration_lib.project_all_constraints for more details.
  • **kwargs: Other args passed to tf.keras.layers.Layer initializer.

Attributes:

  • kernel: TF variable which stores weights of piecewise linear function.
  • missing_output: TF variable which stores output learned for missing input. Or TF Constant which stores missing_output_value if one is provided. Available only if impute_missing is True.
  • activity_regularizer: Optional regularizer function for the output of this layer.
  • dtype
  • dynamic
  • input: Retrieves the input tensor(s) of a layer.

    Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer.

  • input_mask: Retrieves the input mask tensor(s) of a layer.

    Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.

  • input_shape: Retrieves the input shape(s) of a layer.

    Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer, or if all inputs have the same shape.

  • input_spec

  • losses: Losses which are associated with this Layer.

    Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing losses under a tf.GradientTape will propagate gradients back to the corresponding variables.

  • metrics

  • name: Returns the name of this module as passed or determined in the ctor.

    NOTE: This is not the same as the self.name_scope.name which includes parent module names.

  • name_scope: Returns a tf.name_scope instance for this class.

  • non_trainable_variables

  • non_trainable_weights

  • output: Retrieves the output tensor(s) of a layer.

    Only applicable if the layer has exactly one output, i.e. if it is connected to one incoming layer.

  • output_mask: Retrieves the output mask tensor(s) of a layer.

    Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.

  • output_shape: Retrieves the output shape(s) of a layer.

    Only applicable if the layer has one output, or if all outputs have the same shape.

  • submodules: Sequence of all sub-modules.

    Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

a = tf.Module()
b = tf.Module()
c = tf.Module()
a.b = b
b.c = c
assert list(a.submodules) == [b, c]
assert list(b.submodules) == [c]
assert list(c.submodules) == []
  • trainable
  • trainable_variables: Sequence of trainable variables owned by this module and its submodules.

  • trainable_weights

  • updates

  • variables: Returns the list of all layer variables/weights.

    Alias of self.weights.

  • weights: Returns the list of all layer variables/weights.

Example:

calibrator = tfl.layers.PWLCalibration(
    # Key-points of piecewise-linear function.
    input_keypoints=np.linspace(1., 4., num=4),
    # Output can be bounded, e.g. when this layer feeds into a lattice.
    output_min=0.0,
    output_max=2.0,
    # You can specify monotonicity and other shape constraints for the layer.
    monotonicity='increasing',
    # You can specify TFL regularizers as tuple ('regularizer name', l1, l2).
    # You can also pass any keras Regularizer object.
    kernel_regularizer=('hessian', 0.0, 1e-4),
)

Raises:

  • ValueError: If layer hyperparameters are invalid.

Methods

__call__

__call__(
    inputs, *args, **kwargs
)

Wraps call, applying pre- and post-processing steps.

Arguments:

  • inputs: input tensor(s).
  • *args: additional positional arguments to be passed to self.call.
  • **kwargs: additional keyword arguments to be passed to self.call.

Returns:

Output tensor(s).

Note:

  • The following optional keyword arguments are reserved for specific uses:
    • training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference.
    • mask: Boolean input mask.
  • If the layer's call method takes a mask argument (as some Keras layers do), its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support.

Raises:

  • ValueError: if the layer's call method returns None (an invalid value).

assert_constraints

View source

assert_constraints(
    eps=1e-06
)

Asserts that layer weights satisfy all constraints.

In graph mode builds and returns list of assertion ops. Note that ops will be created at the moment when this function is being called. In eager mode directly executes assetions.

Args:

  • eps: Allowed constraints violation.

Returns:

List of assertion ops in graph mode or immideately asserts in eager mode.

build

View source

build(
    input_shape
)

Standard Keras build() method.

compute_mask

compute_mask(
    inputs, mask=None
)

Computes an output mask tensor.

Arguments:

  • inputs: Tensor or list of tensors.
  • mask: Tensor or list of tensors.

Returns:

None or a tensor (or list of tensors, one per output tensor of the layer).

compute_output_shape

View source

compute_output_shape(
    input_shape
)

Standard Keras compute_output_shape() method.

count_params

count_params()

Count the total number of scalars composing the weights.

Returns:

An integer count.

Raises:

  • ValueError: if the layer isn't yet built (in which case its weights aren't yet defined).

from_config

@classmethod
from_config(
    cls, config
)

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Arguments:

  • config: A Python dictionary, typically the output of get_config.

Returns:

A layer instance.

get_config

View source

get_config()

Standard Keras config for serialization.

get_input_at

get_input_at(
    node_index
)

Retrieves the input tensor(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A tensor (or list of tensors if the layer has multiple inputs).

Raises:

  • RuntimeError: If called in Eager mode.

get_input_mask_at

get_input_mask_at(
    node_index
)

Retrieves the input mask tensor(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A mask tensor (or list of tensors if the layer has multiple inputs).

get_input_shape_at

get_input_shape_at(
    node_index
)

Retrieves the input shape(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A shape tuple (or list of shape tuples if the layer has multiple inputs).

Raises:

  • RuntimeError: If called in Eager mode.

get_losses_for

get_losses_for(
    inputs
)

Retrieves losses relevant to a specific set of inputs.

Arguments:

  • inputs: Input tensor or list/tuple of input tensors.

Returns:

List of loss tensors of the layer that depend on inputs.

get_output_at

get_output_at(
    node_index
)

Retrieves the output tensor(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A tensor (or list of tensors if the layer has multiple outputs).

Raises:

  • RuntimeError: If called in Eager mode.

get_output_mask_at

get_output_mask_at(
    node_index
)

Retrieves the output mask tensor(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A mask tensor (or list of tensors if the layer has multiple outputs).

get_output_shape_at

get_output_shape_at(
    node_index
)

Retrieves the output shape(s) of a layer at a given node.

Arguments:

  • node_index: Integer, index of the node from which to retrieve the attribute. E.g. node_index=0 will correspond to the first time the layer was called.

Returns:

A shape tuple (or list of shape tuples if the layer has multiple outputs).

Raises:

  • RuntimeError: If called in Eager mode.

get_updates_for

get_updates_for(
    inputs
)

Retrieves updates relevant to a specific set of inputs.

Arguments:

  • inputs: Input tensor or list/tuple of input tensors.

Returns:

List of update ops of the layer that depend on inputs.

get_weights

get_weights()

Returns the current weights of the layer.

Returns:

Weights values as a list of numpy arrays.

keypoints_outputs

View source

keypoints_outputs()

Returns tensor which corresponds to outputs of layer for keypoints.

set_weights

set_weights(
    weights
)

Sets the weights of the layer, from Numpy arrays.

Arguments:

  • weights: a list of Numpy arrays. The number of arrays and their shape must match number of the dimensions of the weights of the layer (i.e. it should match the output of get_weights).

Raises:

  • ValueError: If the provided weights list does not match the layer's specifications.

with_name_scope

@classmethod
with_name_scope(
    cls, method
)

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 64]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([8, 32]))
# ==> <tf.Tensor: ...>
mod.w
# ==> <tf.Variable ...'my_module/w:0'>

Args:

  • method: The method to wrap.

Returns:

The original method wrapped such that it enters the module's name scope.