tfl.layers.PWLCalibration

Piecewise linear calibration layer.

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:

If units > 1 and split_outputs is True, a length units list of Rank-2 tensors with shape (batch_size, 1). Otherwise, a Rank-2 tensor with shape: (batch_size, units)

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),
)

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.
    split_outputs Whether to split the output tensor into a list of outputs for each unit. Ignored if units < 2.
    input_keypoints_type One of "fixed" or "learned_interior". If "learned_interior", keypoints are initialized to the values in input_keypoints but then allowed to vary during training, with the exception of the first and last keypoint location which are fixed. Convexity can only be imposed with "fixed".
    **kwargs Other args passed to keras.layers.Layer initializer.

    ValueError If layer hyperparameters are invalid.

    • All __init__ arguments.
    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.
    compute_dtype The dtype of the layer's computations.

    This is equivalent to Layer.dtype_policy.compute_dtype. Unless mixed precision is used, this is the same as Layer.dtype, the dtype of the weights.

    Layers automatically cast their inputs to the compute dtype, which causes computations and the output to be in the compute dtype as well. This is done by the base Layer class in Layer.call, so you do not have to insert these casts if implementing your own layer.

    Layers often perform certain internal computations in higher precision when compute_dtype is float16 or bfloat16 for numeric stability. The output will still typically be float16 or bfloat16 in such cases.

    dtype The dtype of the layer weights.

    This is equivalent to Layer.dtype_policy.variable_dtype. Unless mixed precision is used, this is the same as Layer.compute_dtype, the dtype of the layer's computations.

    dtype_policy The dtype policy associated with this layer.

    This is an instance of a tf.keras.mixed_precision.Policy.

    dynamic Whether the layer is dynamic (eager-only); set in the constructor.
    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_spec InputSpec instance(s) describing the input format for this layer.

    When you create a layer subclass, you can set self.input_spec to enable the layer to run input compatibility checks when it is called. Consider a Conv2D layer: it can only be called on a single input tensor of rank 4. As such, you can set, in __init__():

    self.input_spec = tf.keras.layers.InputSpec(ndim=4)
    

    Now, if you try to call the layer on an input that isn't rank 4 (for instance, an input of shape (2,), it will raise a nicely-formatted error:

    ValueError: Input 0 of layer conv2d is incompatible with the layer:
    expected ndim=4, found ndim=1. Full shape received: [2]
    

    Input checks that can be specified via input_spec include:

    • Structure (e.g. a single input, a list of 2 inputs, etc)
    • Shape
    • Rank (ndim)
    • Dtype

    For more information, see tf.keras.layers.InputSpec.

    losses List of losses added using the add_loss() API.

    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.

    class MyLayer(tf.keras.layers.Layer):
      def call(self, inputs):
        self.add_loss(tf.abs(tf.reduce_mean(inputs)))
        return inputs
    l = MyLayer()
    l(np.ones((10, 1)))
    l.losses
    [1.0]
    
    inputs = tf.keras.Input(shape=(10,))
    x = tf.keras.layers.Dense(10)(inputs)
    outputs = tf.keras.layers.Dense(1)(x)
    model = tf.keras.Model(inputs, outputs)
    # Activity regularization.
    len(model.losses)
    0
    model.add_loss(tf.abs(tf.reduce_mean(x)))
    len(model.losses)
    1
    
    inputs = tf.keras.Input(shape=(10,))
    d = tf.keras.layers.Dense(10, kernel_initializer='ones')
    x = d(inputs)
    outputs = tf.keras.layers.Dense(1)(x)
    model = tf.keras.Model(inputs, outputs)
    # Weight regularization.
    model.add_loss(lambda: tf.reduce_mean(d.kernel))
    model.losses
    [<tf.Tensor: shape=(), dtype=float32, numpy=1.0>]
    

    metrics List of metrics attached to the layer.
    name Name of the layer (string), set in the constructor.
    name_scope Returns a tf.name_scope instance for this class.
    non_trainable_weights List of all non-trainable weights tracked by this layer.

    Non-trainable weights are not updated during training. They are expected to be updated manually in call().

    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.

    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
    list(a.submodules) == [b, c]
    True
    list(b.submodules) == [c]
    True
    list(c.submodules) == []
    True
    

    supports_masking Whether this layer supports computing a mask using compute_mask.
    trainable

    trainable_weights List of all trainable weights tracked by this layer.

    Trainable weights are updated via gradient descent during training.

    variable_dtype Alias of Layer.dtype, the dtype of the weights.
    weights Returns the list of all layer variables/weights.

    Methods

    add_loss

    Add loss tensor(s), potentially dependent on layer inputs.

    Some losses (for instance, activity regularization losses) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.losses may be dependent on a and some on b. This method automatically keeps track of dependencies.

    This method can be used inside a subclassed layer or model's call function, in which case losses should be a Tensor or list of Tensors.

    Example:

    class MyLayer(tf.keras.layers.Layer):
      def call(self, inputs):
        self.add_loss(tf.abs(tf.reduce_mean(inputs)))
        return inputs
    

    The same code works in distributed training: the input to add_loss() is treated like a regularization loss and averaged across replicas by the training loop (both built-in Model.fit() and compliant custom training loops).

    The add_loss method can also be called directly on a Functional Model during construction. In this case, any loss Tensors passed to this Model must be symbolic and be able to be traced back to the model's Inputs. These losses become part of the model's topology and are tracked in get_config.

    Example:

    inputs = tf.keras.Input(shape=(10,))
    x = tf.keras.layers.Dense(10)(inputs)
    outputs = tf.keras.layers.Dense(1)(x)
    model = tf.keras.Model(inputs, outputs)
    # Activity regularization.
    model.add_loss(tf.abs(tf.reduce_mean(x)))
    

    If this is not the case for your loss (if, for example, your loss references a Variable of one of the model's layers), you can wrap your loss in a zero-argument lambda. These losses are not tracked as part of the model's topology since they can't be serialized.

    Example:

    inputs = tf.keras.Input(shape=(10,))
    d = tf.keras.layers.Dense(10)
    x = d(inputs)
    outputs = tf.keras.layers.Dense(1)(x)
    model = tf.keras.Model(inputs, outputs)
    # Weight regularization.
    model.add_loss(lambda: tf.reduce_mean(d.kernel))
    

    Args
    losses Loss tensor, or list/tuple of tensors. Rather than tensors, losses may also be zero-argument callables which create a loss tensor.
    **kwargs Used for backwards compatibility only.

    assert_constraints

    View source

    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 assertions.

    Args
    eps Allowed constraints violation.

    Returns
    List of assertion ops in graph mode or immediately asserts in eager mode.

    build

    View source

    Standard Keras build() method.

    build_from_config

    Builds the layer's states with the supplied config dict.

    By default, this method calls the build(config["input_shape"]) method, which creates weights based on the layer's input shape in the supplied config. If your config contains other information needed to load the layer's state, you should override this method.

    Args
    config Dict containing the input shape associated with this layer.

    compute_mask

    Computes an output mask tensor.

    Args
    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

    Standard Keras compute_output_shape() method.

    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

    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).

    Args
    config A Python dictionary, typically the output of get_config.

    Returns
    A layer instance.

    get_build_config

    Returns a dictionary with the layer's input shape.

    This method returns a config dict that can be used by build_from_config(config) to create all states (e.g. Variables and Lookup tables) needed by the layer.

    By default, the config only contains the input shape that the layer was built with. If you're writing a custom layer that creates state in an unusual way, you should override this method to make sure this state is already created when TF-Keras attempts to load its value upon model loading.

    Returns
    A dict containing the input shape associated with the layer.

    get_config

    View source

    Standard Keras config for serialization.

    get_weights

    Returns the current weights of the layer, as NumPy arrays.

    The weights of a layer represent the state of the layer. This function returns both trainable and non-trainable weight values associated with this layer as a list of NumPy arrays, which can in turn be used to load state into similarly parameterized layers.

    For example, a Dense layer returns a list of two values: the kernel matrix and the bias vector. These can be used to set the weights of another Dense layer:

    layer_a = tf.keras.layers.Dense(1,
      kernel_initializer=tf.constant_initializer(1.))
    a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
    layer_a.get_weights()
    [array([[1.],
           [1.],
           [1.]], dtype=float32), array([0.], dtype=float32)]
    layer_b = tf.keras.layers.Dense(1,
      kernel_initializer=tf.constant_initializer(2.))
    b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
    layer_b.get_weights()
    [array([[2.],
           [2.],
           [2.]], dtype=float32), array([0.], dtype=float32)]
    layer_b.set_weights(layer_a.get_weights())
    layer_b.get_weights()
    [array([[1.],
           [1.],
           [1.]], dtype=float32), array([0.], dtype=float32)]
    

    Returns
    Weights values as a list of NumPy arrays.

    keypoints_inputs

    View source

    Returns tensor of keypoint inputs of shape [num_weights, num_units].

    keypoints_outputs

    View source

    Returns tensor of keypoint outputs of shape [num_weights, num_units].

    load_own_variables

    Loads the state of the layer.

    You can override this method to take full control of how the state of the layer is loaded upon calling keras.models.load_model().

    Args
    store Dict from which the state of the model will be loaded.

    save_own_variables

    Saves the state of the layer.

    You can override this method to take full control of how the state of the layer is saved upon calling model.save().

    Args
    store Dict where the state of the model will be saved.

    set_weights

    Sets the weights of the layer, from NumPy arrays.

    The weights of a layer represent the state of the layer. This function sets the weight values from numpy arrays. The weight values should be passed in the order they are created by the layer. Note that the layer's weights must be instantiated before calling this function, by calling the layer.

    For example, a Dense layer returns a list of two values: the kernel matrix and the bias vector. These can be used to set the weights of another Dense layer:

    layer_a = tf.keras.layers.Dense(1,
      kernel_initializer=tf.constant_initializer(1.))
    a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
    layer_a.get_weights()
    [array([[1.],
           [1.],
           [1.]], dtype=float32), array([0.], dtype=float32)]
    layer_b = tf.keras.layers.Dense(1,
      kernel_initializer=tf.constant_initializer(2.))
    b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
    layer_b.get_weights()
    [array([[2.],
           [2.],
           [2.]], dtype=float32), array([0.], dtype=float32)]
    layer_b.set_weights(layer_a.get_weights())
    layer_b.get_weights()
    [array([[1.],
           [1.],
           [1.]], dtype=float32), array([0.], dtype=float32)]
    

    Args
    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

    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], 3]))
        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([1, 2]))
    <tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
    mod.w
    <tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
    numpy=..., dtype=float32)>
    

    Args
    method The method to wrap.

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

    __call__

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

    Args
    *args Positional arguments to be passed to self.call.
    **kwargs 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 TF-Keras layer with masking support.
    • If the layer is not built, the method will call build.

    Raises
    ValueError if the layer's call method returns None (an invalid value).
    RuntimeError if super().__init__() was not called in the constructor.