tfl.layers.CDF

Cumulative Distribution Function (CDF) layer.

Layer takes input of shape (batch_size, input_dim) or (batch_size, 1) and transforms it using input_dim number of cumulative distribution functions, which are naturally monotonic and bounded to the range [0, 1]. If multi dimensional input is provided, each output will be for the corresponding input, otherwise all CDF functions will act on the same input. All units share the same layer configuration, but each has their separate set of trained parameters. The smoothness of the cumulative distribution functions depends on the number of keypoints (i.e. step functions), the activation, and input scaling.

Input shape:

Single input should be a rank-2 tensor with shape: (batch_size, input_dim) or (batch_size, 1).

Output shape:

Rank-2 tensor with shape (batch, input_dim / factor, units) if reduction=='none'. Otherwise a rank-2 tensor with shape (batch_size, units).

Example:

cdf = tfl.layers.CDF(
  num_keypoints=10,
  units=10,
  # You can specify the type of activation to use for the step functions.
  activation="sigmoid",
  # You can specifyc the type of reduction to use across the input dimension.
  reduction="mean",
  # The input scaling type determines whether or not to use a fixed value or
  # to learn the value during training.
  input_scaling_type="fixed",
  # You can make the layer less connected by increasing the pruning factor,
  # which must be a divisor of both the input dimension and units.
  sparsity_factor=1,
)

num_keypoints The number of keypoints (i.e. step functions) to use for each of units CDF functions.
units The output dimension of the layer.
activation The activation function to use for the step functions. One of:

reduction The reduction used for each of the units CDF functions to combine the CDF function output for each input dimension. One of:
  • 'mean': The tf.reduce_mean function.
  • 'geometric_mean': The n'th root of the product of each of the n input dimensions.
  • 'none': No input reduction.
  • input_scaling_init The value used to initialize the input scaling. Defaults to num_keypoints if set to None.
    input_scaling_type The type of input scaling to use. One of:
  • 'fixed': input scaling will be a constant with value input_scaling_init. This will be the value used for all input dimensions.
  • 'learned_shared': input scaling will be a weight learned during training initialized with value input_scaling_init. This will be the value used for all input dimensions.
  • 'learned_per_input': input scaling will be a weight learned during training initialized with value input_scaling_init. A separate value will be learned for each input dimension.
  • input_scaling_monotonicity One of:
  • 'increasing' or 1: input scaling will be constrained to be non-negative such that the output of the layer is monotonic in each dimension.
  • 'none' or 0: input scaling will not be constrained and the output of the layer will no be guaranteed to be monotonic.
  • sparsity_factor The factor by which to prune the connectivity of the layer. If set to 1 there will be no pruning and the layer will be fully connected. If set to >1 the layer will be partially connected where the number of connections will be reduced by this factor. Must be a divisor of both the input_dim and units.
    kernel_initializer None or one of:
  • 'random_uniform': initializes parameters as uniform random functions in the range [0, 1].
  • Any Keras initializer object.
  • **kwargs Any additional keras.layers.Layer arguments.

    • All __init__ arguments.
    kernel TF variable which stores weights of each cdf function.
    input_scaling A constant if input_scaling_type is 'fixed', and a TF variable if set to 'learned'.
    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.

    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

    Computes the output shape of the layer.

    This method will cause the layer's state to be built, if that has not happened before. This requires that the layer will later be used with inputs that match the input shape provided here.

    Args
    input_shape Shape tuple (tuple of integers) or tf.TensorShape, or structure of shape tuples / tf.TensorShape instances (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.

    Returns
    A tf.TensorShape instance or structure of tf.TensorShape instances.

    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 get_config() method.

    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.

    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.