TopologicalVariationalAutoencoder

latent.models.vae.TopologicalVariationalAutoencoder

Variational autoencoder model with topological loss on latent space

__init__(self, decoder=None, name='variational_autoencoder', x_dim=None, latent_dim=50, encoder_units=[128, 128], decoder_units=[128, 128], reconstruction_loss=None, use_conditions=False, kld_weight=1e-05, topo_weight=1.0, prior='normal', latent_dist='independent', iaf_units=[256, 256], n_pseudoinputs=200, **kwargs) special

Parameters:

Name	Type	Description	Default
decoder	Model	Keras/tensorflow model object that inputs the latent space and outputs the reconstructed data. If not provided, a default model will be constructed from the arguments.	None
name	str	String indicating the name of the model.	'variational_autoencoder'
x_dim	int	Integer indicating the number of features in the input data.	None
latent_dim	int	Integer indicating the number of dimensions in the latent space.	50
encoder_units	Iterable[int]	Integer list indicating the number of units of the encoder layers. Only used if encoder is not provided.	[128, 128]
decoder_units	Iterable[int]	An integer list indicating the number of units of the decoder layers. Only used if decoder is not provided.	[128, 128]
reconstruction_loss	Callable	Loss function applied to the reconstructed data and to be added by the decoder. Only used if decoder is not provided. Can also be added later by calling compile().	None
use_conditions	bool	Boolean, whether to force the unpacking of conditions from the inputs.	False
kld_weight	float	Float indicating the weight of the KL Divergence regularization loss.	1e-05
topo_weight	float	Float indicating the weight of the topological loss.	1.0
prior	Literal['normal', 'iaf', 'vamp']	The choice of prior distribution. One of the following: 'normal' - A unit gaussian (normal) distribution. 'iaf' - A unit gaussian with a Inverse Autoregressive Flows bijector (Kingma 2016) 'vamp' - A variational mixture of posteriors (VAMP) prior (Tomczak 2017)	'normal'
latent_dist	Literal['independent', 'multivariate']	The choice of latent distribution. One of the following: 'independent' - A independent normal produced by tfpl.IndependentNormal. 'multivariate' - A multivariate normal produced by tfpl.MultivariateNormalTriL.	'independent'
iaf_units	Iterable[int]	Integer list indicating the units in the IAF bijector network. Only used if prior = 'iaf'.	[256, 256]
n_pseudoinputs	int	Integer indicating the number of pseudoinputs for the VAMP prior. Only used if prior = 'vamp'.	200
**kwargs		Other arguments passed on to DenseStack for constructung encoder/ decoder networks.	{}

call(self, inputs, training=None) inherited

Full forward pass through model

compile(self, optimizer='adam', loss=None, **kwargs) inherited

Configures the model for training.

Examples:

model.compile(optimizer=tf.keras.optimizer.Adam(learning_rate=1e-3),
              loss=tf.keras.losses.BinaryCrossentropy(),
              metrics=[tf.keras.metrics.BinaryAccuracy(),
                       tf.keras.metrics.FalseNegatives()])

Parameters:

Name	Type	Description	Default
optimizer		String (name of optimizer) or optimizer instance. See tf.keras.optimizers.	'adam'
loss		Loss function. Maybe be a string (name of loss function), or a tf.keras.losses.Loss instance. See tf.keras.losses. A loss function is any callable with the signature loss = fn(y_true, y_pred), where y_true are the ground truth values, and y_pred are the model's predictions. y_true should have shape (batch_size, d0, .. dN) (except in the case of sparse loss functions such as sparse categorical crossentropy which expects integer arrays of shape (batch_size, d0, .. dN-1)). y_pred should have shape (batch_size, d0, .. dN). The loss function should return a float tensor. If a custom Loss instance is used and reduction is set to None, return value has shape (batch_size, d0, .. dN-1) i.e. per-sample or per-timestep loss values; otherwise, it is a scalar. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of losses. The loss value that will be minimized by the model will then be the sum of all individual losses, unless loss_weights is specified.	None
metrics		List of metrics to be evaluated by the model during training and testing. Each of this can be a string (name of a built-in function), function or a tf.keras.metrics.Metric instance. See tf.keras.metrics. Typically you will use metrics=['accuracy']. A function is any callable with the signature result = fn(y_true, y_pred). To specify different metrics for different outputs of a multi-output model, you could also pass a dictionary, such as metrics={'output_a': 'accuracy', 'output_b': ['accuracy', 'mse']}. You can also pass a list to specify a metric or a list of metrics for each output, such as metrics=[['accuracy'], ['accuracy', 'mse']] or metrics=['accuracy', ['accuracy', 'mse']]. When you pass the strings 'accuracy' or 'acc', we convert this to one of tf.keras.metrics.BinaryAccuracy, tf.keras.metrics.CategoricalAccuracy, tf.keras.metrics.SparseCategoricalAccuracy based on the loss function used and the model output shape. We do a similar conversion for the strings 'crossentropy' and 'ce' as well.	required
loss_weights		Optional list or dictionary specifying scalar coefficients (Python floats) to weight the loss contributions of different model outputs. The loss value that will be minimized by the model will then be the weighted sum of all individual losses, weighted by the loss_weights coefficients. If a list, it is expected to have a 1:1 mapping to the model's outputs. If a dict, it is expected to map output names (strings) to scalar coefficients.	required
weighted_metrics		List of metrics to be evaluated and weighted by sample_weight or class_weight during training and testing.	required
run_eagerly		Bool. Defaults to False. If True, this Model's logic will not be wrapped in a tf.function. Recommended to leave this as None unless your Model cannot be run inside a tf.function. run_eagerly=True is not supported when using tf.distribute.experimental.ParameterServerStrategy.	required
steps_per_execution		Int. Defaults to 1. The number of batches to run during each tf.function call. Running multiple batches inside a single tf.function call can greatly improve performance on TPUs or small models with a large Python overhead. At most, one full epoch will be run each execution. If a number larger than the size of the epoch is passed, the execution will be truncated to the size of the epoch. Note that if steps_per_execution is set to N, Callback.on_batch_begin and Callback.on_batch_end methods will only be called every N batches (i.e. before/after each tf.function execution).	required
**kwargs		Arguments supported for backwards compatibility only.	{}

Exceptions:

Type	Description
ValueError	In case of invalid arguments for optimizer, loss or metrics.

fit(self, x, y=None, **kwargs) inherited

Trains the model for a fixed number of epochs (iterations on a dataset).

Parameters:

Name	Type	Description	Default
x		Input data. It could be: - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A dict mapping input names to the corresponding array/tensors, if the model has named inputs. - A tf.data dataset. Should return a tuple of either (inputs, targets) or (inputs, targets, sample_weights). - A generator or keras.utils.Sequence returning (inputs, targets) or (inputs, targets, sample_weights). - A tf.keras.utils.experimental.DatasetCreator, which wraps a callable that takes a single argument of type tf.distribute.InputContext, and returns a tf.data.Dataset. DatasetCreator should be used when users prefer to specify the per-replica batching and sharding logic for the Dataset. See tf.keras.utils.experimental.DatasetCreator doc for more information. A more detailed description of unpacking behavior for iterator types (Dataset, generator, Sequence) is given below. If using tf.distribute.experimental.ParameterServerStrategy, only DatasetCreator type is supported for x.	required
y		Target data. Like the input data x, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with x (you cannot have Numpy inputs and tensor targets, or inversely). If x is a dataset, generator, or keras.utils.Sequence instance, y should not be specified (since targets will be obtained from x).	None
batch_size		Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32. Do not specify the batch_size if your data is in the form of datasets, generators, or keras.utils.Sequence instances (since they generate batches).	required
epochs		Integer. Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided. Note that in conjunction with initial_epoch, epochs is to be understood as "final epoch". The model is not trained for a number of iterations given by epochs, but merely until the epoch of index epochs is reached.	required
verbose		'auto', 0, 1, or 2. Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch. 'auto' defaults to 1 for most cases, but 2 when used with ParameterServerStrategy. Note that the progress bar is not particularly useful when logged to a file, so verbose=2 is recommended when not running interactively (eg, in a production environment).	required
callbacks		List of keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks. Note tf.keras.callbacks.ProgbarLogger and tf.keras.callbacks.History callbacks are created automatically and need not be passed into model.fit. tf.keras.callbacks.ProgbarLogger is created or not based on verbose argument to model.fit. Callbacks with batch-level calls are currently unsupported with tf.distribute.experimental.ParameterServerStrategy, and users are advised to implement epoch-level calls instead with an appropriate steps_per_epoch value.	required
validation_split		Float between 0 and 1. Fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch. The validation data is selected from the last samples in the x and y data provided, before shuffling. This argument is not supported when x is a dataset, generator or keras.utils.Sequence instance. validation_split is not yet supported with tf.distribute.experimental.ParameterServerStrategy.	required
validation_data		Data on which to evaluate the loss and any model metrics at the end of each epoch. The model will not be trained on this data. Thus, note the fact that the validation loss of data provided using validation_split or validation_data is not affected by regularization layers like noise and dropout. validation_data will override validation_split. validation_data could be: - A tuple (x_val, y_val) of Numpy arrays or tensors. - A tuple (x_val, y_val, val_sample_weights) of NumPy arrays. - A tf.data.Dataset. - A Python generator or keras.utils.Sequence returning (inputs, targets) or (inputs, targets, sample_weights). validation_data is not yet supported with tf.distribute.experimental.ParameterServerStrategy.	required
shuffle		Boolean (whether to shuffle the training data before each epoch) or str (for 'batch'). This argument is ignored when x is a generator or an object of tf.data.Dataset. 'batch' is a special option for dealing with the limitations of HDF5 data; it shuffles in batch-sized chunks. Has no effect when steps_per_epoch is not None.	required
class_weight		Optional dictionary mapping class indices (integers) to a weight (float) value, used for weighting the loss function (during training only). This can be useful to tell the model to "pay more attention" to samples from an under-represented class.	required
sample_weight		Optional Numpy array of weights for the training samples, used for weighting the loss function (during training only). You can either pass a flat (1D) Numpy array with the same length as the input samples (1:1 mapping between weights and samples), or in the case of temporal data, you can pass a 2D array with shape (samples, sequence_length), to apply a different weight to every timestep of every sample. This argument is not supported when x is a dataset, generator, or keras.utils.Sequence instance, instead provide the sample_weights as the third element of x.	required
initial_epoch		Integer. Epoch at which to start training (useful for resuming a previous training run).	required
steps_per_epoch		Integer or None. Total number of steps (batches of samples) before declaring one epoch finished and starting the next epoch. When training with input tensors such as TensorFlow data tensors, the default None is equal to the number of samples in your dataset divided by the batch size, or 1 if that cannot be determined. If x is a tf.data dataset, and 'steps_per_epoch' is None, the epoch will run until the input dataset is exhausted. When passing an infinitely repeating dataset, you must specify the steps_per_epoch argument. If steps_per_epoch=-1 the training will run indefinitely with an infinitely repeating dataset. This argument is not supported with array inputs. When using tf.distribute.experimental.ParameterServerStrategy: * steps_per_epoch=None is not supported.	required
validation_steps		Only relevant if validation_data is provided and is a tf.data dataset. Total number of steps (batches of samples) to draw before stopping when performing validation at the end of every epoch. If 'validation_steps' is None, validation will run until the validation_data dataset is exhausted. In the case of an infinitely repeated dataset, it will run into an infinite loop. If 'validation_steps' is specified and only part of the dataset will be consumed, the evaluation will start from the beginning of the dataset at each epoch. This ensures that the same validation samples are used every time.	required
validation_batch_size		Integer or None. Number of samples per validation batch. If unspecified, will default to batch_size. Do not specify the validation_batch_size if your data is in the form of datasets, generators, or keras.utils.Sequence instances (since they generate batches).	required
validation_freq		Only relevant if validation data is provided. Integer or collections.abc.Container instance (e.g. list, tuple, etc.). If an integer, specifies how many training epochs to run before a new validation run is performed, e.g. validation_freq=2 runs validation every 2 epochs. If a Container, specifies the epochs on which to run validation, e.g. validation_freq=[1, 2, 10] runs validation at the end of the 1st, 2nd, and 10th epochs.	required
max_queue_size		Integer. Used for generator or keras.utils.Sequence input only. Maximum size for the generator queue. If unspecified, max_queue_size will default to 10.	required
workers		Integer. Used for generator or keras.utils.Sequence input only. Maximum number of processes to spin up when using process-based threading. If unspecified, workers will default to 1.	required
use_multiprocessing		Boolean. Used for generator or keras.utils.Sequence input only. If True, use process-based threading. If unspecified, use_multiprocessing will default to False. Note that because this implementation relies on multiprocessing, you should not pass non-picklable arguments to the generator as they can't be passed easily to children processes.	required

Unpacking behavior for iterator-like inputs: A common pattern is to pass a tf.data.Dataset, generator, or tf.keras.utils.Sequence to the x argument of fit, which will in fact yield not only features (x) but optionally targets (y) and sample weights. Keras requires that the output of such iterator-likes be unambiguous. The iterator should return a tuple of length 1, 2, or 3, where the optional second and third elements will be used for y and sample_weight respectively. Any other type provided will be wrapped in a length one tuple, effectively treating everything as 'x'. When yielding dicts, they should still adhere to the top-level tuple structure. e.g. ({"x0": x0, "x1": x1}, y). Keras will not attempt to separate features, targets, and weights from the keys of a single dict. A notable unsupported data type is the namedtuple. The reason is that it behaves like both an ordered datatype (tuple) and a mapping datatype (dict). So given a namedtuple of the form: namedtuple("example_tuple", ["y", "x"]) it is ambiguous whether to reverse the order of the elements when interpreting the value. Even worse is a tuple of the form: namedtuple("other_tuple", ["x", "y", "z"]) where it is unclear if the tuple was intended to be unpacked into x, y, and sample_weight or passed through as a single element to x. As a result the data processing code will simply raise a ValueError if it encounters a namedtuple. (Along with instructions to remedy the issue.)

Returns:

Type	Description
	A History object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).

Exceptions:

Type	Description
RuntimeError	If the model was never compiled or,
ValueError	In case of mismatch between the provided input data and what the model expects or when the input data is empty.

transform(self, x, conditions=None) inherited

Map data (x) to latent space (z).

Parameters:

Name	Type	Description	Default
x		A numpy array with input data.	required
conditions		A numpy array with conditions.	None

Returns:

Type	Description
	A numpy array with the coordinates of the input data in latent space.