View source on GitHub |

## Class `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:

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

.

#### Attributes:

All

`__init__`

arguments.: TF variable which stores weights of piecewise linear function.`kernel`

: TF variable which stores output learned for missing input. Or TF Constant which stores`missing_output`

`missing_output_value`

if one is provided. Available only if`impute_missing`

is True.

#### 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),
)
```

`__init__`

```
__init__(
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
)
```

Initializes an instance of `PWLCalibration`

.

#### Args:

: Ordered list of keypoints of piecewise linear function. Can be anything accepted by tf.convert_to_tensor().`input_keypoints`

: Output dimension of the layer. See class comments for details.`units`

: Minimum output of calibrator.`output_min`

: Maximum output of calibrator.`output_max`

: For monotonic calibrators ensures that output_min is reached.`clamp_min`

: For monotonic calibrators ensures that output_max is reached.`clamp_max`

: 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.`monotonicity`

: 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`convexity`

`num_projection_iterations`

if convexity is specified, especially with larger number of keypoints.: 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.`is_cyclic`

: None or one of:`kernel_initializer`

- 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.

- String
: None or single element or list of following:`kernel_regularizer`

- 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.

- Tuple
: Whether to learn an output for cases where input data is missing. If set to True, either`impute_missing`

`missing_input_value`

should be initialized, or the`call()`

method should get pair of tensors. See class input shape description for more details.: If set, all inputs which are equal to this value will be considered as missing. Can not be set if`missing_input_value`

`impute_missing`

is False.: If set, instead of learning output for missing inputs, simply maps them into this value. Can not be set if`missing_output_value`

`impute_missing`

is False.: 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`num_projection_iterations`

`tfl.pwl_calibration_lib.project_all_constraints`

for more details.: Other args passed to`**kwargs`

`tf.keras.layers.Layer`

initializer.

#### Raises:

: If layer hyperparameters are invalid.`ValueError`

## Properties

`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.

#### Returns:

Input tensor or list of input tensors.

#### Raises:

: If called in Eager mode.`RuntimeError`

: If no inbound nodes are found.`AttributeError`

`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.

#### Returns:

Input mask tensor (potentially None) or list of input mask tensors.

#### Raises:

: if the layer is connected to more than one incoming layers.`AttributeError`

`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.

#### Returns:

Input shape, as an integer shape tuple (or list of shape tuples, one tuple per input tensor).

#### Raises:

: if the layer has no defined input_shape.`AttributeError`

: if called in Eager mode.`RuntimeError`

`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.

#### Returns:

A list of tensors.

`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.

#### Returns:

Output tensor or list of output tensors.

#### Raises:

: if the layer is connected to more than one incoming layers.`AttributeError`

: if called in Eager mode.`RuntimeError`

`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.

#### Returns:

Output mask tensor (potentially None) or list of output mask tensors.

#### Raises:

: if the layer is connected to more than one incoming layers.`AttributeError`

`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.

#### Returns:

Output shape, as an integer shape tuple (or list of shape tuples, one tuple per output tensor).

#### Raises:

: if the layer has no defined output shape.`AttributeError`

: if called in Eager mode.`RuntimeError`

`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) == []
```

#### Returns:

A sequence of all submodules.

`trainable`

`trainable_variables`

Sequence of trainable variables owned by this module and its submodules.

#### Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

`trainable_weights`

`updates`

`variables`

Returns the list of all layer variables/weights.

Alias of `self.weights`

.

#### Returns:

A list of variables.

`weights`

Returns the list of all layer variables/weights.

#### Returns:

A list of variables.

## Methods

`__call__`

```
__call__(
inputs,
*args,
**kwargs
)
```

Wraps `call`

, applying pre- and post-processing steps.

#### Arguments:

: input tensor(s).`inputs`

: additional positional arguments to be passed to`*args`

`self.call`

.: additional keyword arguments to be passed to`**kwargs`

`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:

: if the layer's`ValueError`

`call`

method returns None (an invalid value).

`assert_constraints`

```
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:

: Allowed constraints violation.`eps`

#### Returns:

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

`build`

```
build(input_shape)
```

Standard Keras build() method.

`compute_mask`

```
compute_mask(
inputs,
mask=None
)
```

Computes an output mask tensor.

#### Arguments:

: Tensor or list of tensors.`inputs`

: Tensor or list of tensors.`mask`

#### Returns:

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

`compute_output_shape`

```
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:

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

`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:

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

#### Returns:

A layer instance.

`get_config`

```
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:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: If called in Eager mode.`RuntimeError`

`get_input_mask_at`

```
get_input_mask_at(node_index)
```

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

#### Arguments:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: If called in Eager mode.`RuntimeError`

`get_losses_for`

```
get_losses_for(inputs)
```

Retrieves losses relevant to a specific set of inputs.

#### Arguments:

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

#### 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:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: If called in Eager mode.`RuntimeError`

`get_output_mask_at`

```
get_output_mask_at(node_index)
```

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

#### Arguments:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: Integer, index of the node from which to retrieve the attribute. E.g.`node_index`

`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:

: If called in Eager mode.`RuntimeError`

`get_updates_for`

```
get_updates_for(inputs)
```

Retrieves updates relevant to a specific set of inputs.

#### Arguments:

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

#### 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`

```
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:

: 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`weights`

`get_weights`

).

#### Raises:

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

`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.Variable`

s and `tf.Tensor`

s whose
names included the module name:

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

#### Args:

: The method to wrap.`method`

#### Returns:

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