# tfl.layers.Linear

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/linear_layer.py#L42-L347) |

Layer which represents linear function.

    tfl.layers.Linear(
        num_input_dims,
        units=1,
        monotonicities=None,
        monotonic_dominances=None,
        range_dominances=None,
        input_min=None,
        input_max=None,
        use_bias=True,
        normalization_order=None,
        kernel_initializer='random_uniform',
        bias_initializer='random_uniform',
        kernel_regularizer=None,
        bias_regularizer=None,
        **kwargs
    )

Monotonicity can be specified for any input dimension in which case learned
weight for that dimension is guaranteed to be either non negative for
increasing or non positive for decreasing monotonicity.

Monotonic dominance can be specified for any pair of dimensions referred to as
*dominant* and *weak* dimensions such that the effect (slope) in the direction
of the *dominant* dimension to be greater than that of the *weak* dimension
for any point. Both dominant and weak dimensions must be increasing.

Range dominance can be specified for any pair of *dominant* and *weak*
dimensions such that the range of possible outputs to be greater if one varies
the *dominant* dimension than if one varies the *weak* dimension for any
point. We require the slope of the *dominant* dimension scaled by its input
range to be greater than the slope of the *weak* dimension similarly scaled by
its input range. Both dimensions must have the same direction of monotonicity
and their input min and max must be provided.

Weights can be constrained to have a fixed norm.

<br />

<br />

| ## Input shape ||
|---|---|
| <br /> - if `units == 1`: tensor of shape: `(batch_size, num_input_dims)`. - if `units > 1`: tensor of shape: `(batch_size, units, num_input_dims)` ||

<br />

#### Output shape:

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

#### Example:

    layer = tfl.layers.Linear(
        num_input_dims=8,
        # Monotonicity constraints can be defined per dimension or for all dims.
        monotonicities='increasing',
        use_bias=True,
        # You can force the L1 norm to be 1. Since this is a monotonic layer,
        # the coefficients will sum to 1, making this a "weighted average".
        normalization_order=1)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `num_input_dims` | Number of input dimensions. |
| `units` | Output dimension of the layer. |
| `monotonicities` | None or list or tuple of length 'num_input_dims' of {'decreasing', 'none', 'increasing', -1, 0, 1} which specifies if the model output should be monotonic in corresponding feature, using 'increasing' or 1 to indicate increasing monotonicity, 'decreasing' or -1 to indicate decreasing monotonicity and 'none' or 0 to indicate no monotonicity constraints. In case of decreasing monotonicity corresponding weight will be constrained to be non positive, in case of increasing non-negative. Instead of a list or tuple single value can be specified to indicate the monotonicity constraint across all dimensions. |
| `monotonic_dominances` | None or list of two-element tuples. First element is the index of the dominant dimension. Second element is the index of the weak dimension. |
| `range_dominances` | None or list of two-element tuples. First element is the index of the dominant dimension. Second element is the index of the weak dimension. Both dominant and weak dimensions must have input_min and input_max set. |
| `input_min` | None of list or tuple of length 'num_input_dims' of either 'none' or float which specifies the minimum value to clip by for each dimension. |
| `input_max` | None of list or tuple of length 'num_input_dims' of either 'none' or float which specifies the maximum value to clip by for each dimension. |
| `use_bias` | Whether linear function has bias. |
| `normalization_order` | If specified learned weights will be adjusted to have norm 1. Norm will be computed by: `tf.norm(tensor, ord=normalization_order)`. |
| `kernel_initializer` | Any keras initializer to be applied to kernel. |
| `bias_initializer` | Any keras initializer to be applied to bias. Only valid if `use_bias == True`. |
| `kernel_regularizer` | None or single element or list of any Keras regularizer objects. |
| `bias_regularizer` | None or single element or list of any Keras regularizer objects. |
| `**kwargs` | Other args passed to [`keras.layers.Layer`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer) initializer. |

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | if monotonicity specified incorrectly. |

<br />

<br />

| ## Attributes ||
|---|---|
| <br /> - All `__init__`arguments. ||
| `kernel` | layer's kernel. |
| `bias` | layer's bias. Only available if `use_bias == 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`](https://www.tensorflow.org/api_docs/python/tf/keras/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`](https://www.tensorflow.org/probability/oryx/api_docs/python/oryx/core/state/Module#__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. <br /> This is equivalent to `Layer.dtype_policy.variable_dtype`. Unless mixed precision is used, this is the same as [`Layer.compute_dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer#compute_dtype), the dtype of the layer's computations. |
| `dtype_policy` | The dtype policy associated with this layer. <br /> This is an instance of a [`tf.keras.mixed_precision.Policy`](https://www.tensorflow.org/api_docs/python/tf/keras/DTypePolicy). |
| `dynamic` | Whether the layer is dynamic (eager-only); set in the constructor. |
| `input` | Retrieves the input tensor(s) of a layer. <br /> 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. <br /> 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`](https://www.tensorflow.org/api_docs/python/tf/keras/InputSpec). |
| `losses` | List of losses added using the `add_loss()` API. <br /> Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing `losses` under a [`tf.GradientTape`](https://www.tensorflow.org/api_docs/python/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>] <br /> |
| `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`](https://www.tensorflow.org/api_docs/python/tf/name_scope) instance for this class. |
| `non_trainable_weights` | List of all non-trainable weights tracked by this layer. <br /> 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. <br /> 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. <br /> 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 <br /> |
| `supports_masking` | Whether this layer supports computing a mask using `compute_mask`. |
| `trainable` | <br /> <br /> |
| `trainable_weights` | List of all trainable weights tracked by this layer. <br /> Trainable weights are updated via gradient descent during training. |
| `variable_dtype` | Alias of [`Layer.dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer#dtype), the dtype of the weights. |
| `weights` | Returns the list of all layer variables/weights. |

<br />

## Methods

### `add_loss`

    add_loss(
        losses, **kwargs
    )

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()`](https://www.tensorflow.org/api_docs/python/tf/keras/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 `Input`s.
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))

<br />

<br />

<br />

| 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. |

<br />

### `assert_constraints`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/linear_layer.py#L327-L347)

    assert_constraints(
        eps=0.0001
    )

Asserts that weights satisfy all constraints.

In graph mode builds and returns list of assertion ops.
In eager mode directly executes assertions.

<br />

<br />

<br />

| Args ||
|---|---|
| `eps` | Allowed constraints violation. |

<br />

<br />

<br />

<br />

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

<br />

### `build`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/linear_layer.py#L197-L271)

    build(
        input_shape
    )

Standard Keras build() method.

<br />

<br />

<br />

| Args ||
|---|---|
| `input_shape` | Must be: (batch_size, num_input_dims) if units == 1, or (batch_size, units, num_input_dims) if units \> 1. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If shape is invalid. |

<br />

### `build_from_config`

    build_from_config(
        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.

<br />

<br />

<br />

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

<br />

### `compute_mask`

    compute_mask(
        inputs, mask=None
    )

Computes an output mask tensor.

<br />

<br />

<br />

| Args ||
|---|---|
| `inputs` | Tensor or list of tensors. |
| `mask` | Tensor or list of tensors. |

<br />

<br />

<br />

<br />

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

<br />

### `compute_output_shape`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/linear_layer.py#L288-L291)

    compute_output_shape(
        input_shape
    )

Standard Keras compute_output_shape() method.

### `count_params`

    count_params()

Count the total number of scalars composing the weights.

<br />

<br />

<br />

| Returns ||
|---|---|
| An integer count. ||

<br />

<br />

<br />

<br />

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

<br />

### `from_config`

    @classmethod
    from_config(
        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`).

<br />

<br />

<br />

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

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A layer instance. ||

<br />

### `get_build_config`

    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.

<br />

<br />

<br />

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

<br />

### `get_config`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/linear_layer.py#L293-L323)

    get_config()

Standard Keras get_config() method.

### `get_weights`

    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)]

<br />

<br />

<br />

| Returns ||
|---|---|
| Weights values as a list of NumPy arrays. ||

<br />

### `load_own_variables`

    load_own_variables(
        store
    )

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()`](https://www.tensorflow.org/api_docs/python/tf/keras/models/load_model).

<br />

<br />

<br />

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

<br />

### `save_own_variables`

    save_own_variables(
        store
    )

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()`.

<br />

<br />

<br />

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

<br />

### `set_weights`

    set_weights(
        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)]

<br />

<br />

<br />

| 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`). |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If the provided weights list does not match the layer's specifications. |

<br />

### `with_name_scope`

    @classmethod
    with_name_scope(
        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], 3]))
        return tf.matmul(x, self.w)

Using the above module would produce [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s and [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)s 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)>

<br />

<br />

<br />

| Args ||
|---|---|
| `method` | The method to wrap. |

<br />

<br />

<br />

<br />

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

<br />

### `__call__`

    __call__(
        *args, **kwargs
    )

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

<br />

<br />

<br />

| Args ||
|---|---|
| `*args` | Positional arguments to be passed to `self.call`. |
| `**kwargs` | Keyword arguments to be passed to `self.call`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Output tensor(s). ||

<br />

<br />

<br />

| Note ||
|---|---|
| <br /> - 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`. ||

<br />

<br />

<br />

<br />

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

<br />