def create_vrnn(generative_class=base.ConditionalNormalDistribution, batch_size=2, data_size=3, rnn_hidden_size=4, latent_size=5, fcnet_hidden_size=7, encoded_data_size=9, encoded_latent_size=11, num_timesteps=7, data_lengths=(7, 4), use_tilt=False, random_seed=None): """Creates a VRNN and some dummy data to feed it for testing purposes. Args: generative_class: The class of the generative distribution. batch_size: The number of elements per batch. data_size: The dimension of the vectors that make up the data sequences. rnn_hidden_size: The hidden state dimension of the RNN that forms the deterministic part of this VRNN. latent_size: The size of the stochastic latent state of the VRNN. fcnet_hidden_size: The size of the hidden layer of the fully connected networks that parameterize the conditional probability distributions of the VRNN. encoded_data_size: The size of the output of the data encoding network. encoded_latent_size: The size of the output of the latent state encoding network. num_timesteps: The maximum number of timesteps in the data. data_lengths: A tuple of size batch_size that contains the desired lengths of each sequence in the dummy data. use_tilt: Use a tilting function. random_seed: A random seed to feed the VRNN, mainly useful for testing purposes. Returns: model: A VRNN object. inputs: A Tensor of shape [num_timesteps, batch_size, data_size], the inputs to the model, also known as the observations. targets: A Tensor of shape [num_timesteps, batch_size, data_size], the desired outputs of the model. lengths: A Tensor of shape [batch_size], the lengths of the sequences in the batch. """ fcnet_hidden_sizes = [fcnet_hidden_size] initializers = {"w": tf.contrib.layers.xavier_initializer(seed=random_seed), "b": tf.zeros_initializer()} model = vrnn.create_vrnn( data_size, latent_size, generative_class, rnn_hidden_size=rnn_hidden_size, fcnet_hidden_sizes=fcnet_hidden_sizes, encoded_data_size=encoded_data_size, encoded_latent_size=encoded_latent_size, use_tilt=use_tilt, initializers=initializers, random_seed=random_seed) inputs = tf.random_uniform([num_timesteps, batch_size, data_size], seed=random_seed, dtype=tf.float32) targets = tf.random_uniform([num_timesteps, batch_size, data_size], seed=random_seed, dtype=tf.float32) lengths = tf.constant(data_lengths, dtype=tf.int32) return model, inputs, targets, lengths
def create_vrnn(generative_class=base.ConditionalNormalDistribution, batch_size=2, data_size=3, rnn_hidden_size=4, latent_size=5, fcnet_hidden_size=7, encoded_data_size=9, encoded_latent_size=11, num_timesteps=7, data_lengths=(7, 4), use_tilt=False, random_seed=None): """Creates a VRNN and some dummy data to feed it for testing purposes. Args: generative_class: The class of the generative distribution. batch_size: The number of elements per batch. data_size: The dimension of the vectors that make up the data sequences. rnn_hidden_size: The hidden state dimension of the RNN that forms the deterministic part of this VRNN. latent_size: The size of the stochastic latent state of the VRNN. fcnet_hidden_size: The size of the hidden layer of the fully connected networks that parameterize the conditional probability distributions of the VRNN. encoded_data_size: The size of the output of the data encoding network. encoded_latent_size: The size of the output of the latent state encoding network. num_timesteps: The maximum number of timesteps in the data. data_lengths: A tuple of size batch_size that contains the desired lengths of each sequence in the dummy data. use_tilt: Use a tilting function. random_seed: A random seed to feed the VRNN, mainly useful for testing purposes. Returns: model: A VRNN object. inputs: A Tensor of shape [num_timesteps, batch_size, data_size], the inputs to the model, also known as the observations. targets: A Tensor of shape [num_timesteps, batch_size, data_size], the desired outputs of the model. lengths: A Tensor of shape [batch_size], the lengths of the sequences in the batch. """ fcnet_hidden_sizes = [fcnet_hidden_size] initializers = {"w": tf.contrib.layers.xavier_initializer(seed=random_seed), "b": tf.zeros_initializer()} model = vrnn.create_vrnn( data_size, latent_size, generative_class, rnn_hidden_size=rnn_hidden_size, fcnet_hidden_sizes=fcnet_hidden_sizes, encoded_data_size=encoded_data_size, encoded_latent_size=encoded_latent_size, use_tilt=use_tilt, initializers=initializers, random_seed=random_seed) inputs = tf.random_uniform([num_timesteps, batch_size, data_size], seed=random_seed, dtype=tf.float32) targets = tf.random_uniform([num_timesteps, batch_size, data_size], seed=random_seed, dtype=tf.float32) lengths = tf.constant(data_lengths, dtype=tf.int32) return model, inputs, targets, lengths
def dummmy_dataset_and_model_fn(self, *unused_args, **unused_kwargs): # We ignore the arguments in the dummy but need to preserve prototype. batch_elements = 5 sequence_length = 4 data_dimensions = 3 dataset = tf.data.Dataset.from_tensors( tf.zeros((sequence_length, batch_elements, data_dimensions), dtype=tf.float32)) inputs = dataset.make_one_shot_iterator().get_next() targets = tf.zeros_like(inputs) lengths = tf.constant([sequence_length] * batch_elements) mean = tf.constant((0.0, 0.0, 0.0)) model = vrnn.create_vrnn(data_dimensions, 1, base.ConditionalNormalDistribution) return inputs, targets, lengths, model, mean
def create_dataset_and_model(config, split, shuffle, repeat): """Creates the dataset and model for a given config. Args: config: A configuration object with config values accessible as properties. Most likely a FLAGS object. This function expects the properties batch_size, dataset_path, dataset_type, and latent_size to be defined. split: The dataset split to load. shuffle: If true, shuffle the dataset randomly. repeat: If true, repeat the dataset endlessly. Returns: inputs: A batch of input sequences represented as a dense Tensor of shape [time, batch_size, data_dimension]. targets: A batch of target sequences represented as a dense Tensor of shape [time, batch_size, data_dimension]. lens: An int Tensor of shape [batch_size] representing the lengths of each sequence in the batch. model: A vrnn.VRNNCell model object. Raises: ValueError: if the config is invalid. """ sigma_min = 0.0 if config.dataset_type == "pianoroll": inputs, targets, lengths, mean = datasets.create_pianoroll_dataset( config.dataset_path, split, config.batch_size, shuffle=shuffle, repeat=repeat) # Convert the mean of the training set to logit space so it can be used to # initialize the bias of the generative distribution. emission_bias_init = -tf.log( 1. / tf.clip_by_value(mean, 0.0001, 0.9999) - 1) emission_distribution_class = base.ConditionalBernoulliDistribution elif config.dataset_type == "speech": inputs, targets, lengths = datasets.create_speech_dataset( config.dataset_path, config.batch_size, samples_per_timestep=config.data_dimension, prefetch_buffer_size=1, shuffle=False, repeat=False) # There is no bias for the generative distribution because the test set # is assumed to be already standardized with the training set statistics. mean = None emission_bias_init = None emission_distribution_class = base.ConditionalNormalDistribution if config.model == "vrnn": model = vrnn.create_vrnn(inputs.get_shape().as_list()[2], config.latent_size, emission_distribution_class, emission_bias_init=emission_bias_init, proposal_type=config.proposal_type, sigma_min=sigma_min, raw_sigma_bias=0.5, use_tilt=(config.bound == "fivo-aux")) elif config.model == "srnn": model = srnn.create_srnn(inputs.get_shape().as_list()[2], config.latent_size, emission_distribution_class, emission_bias_init=emission_bias_init, proposal_type=config.proposal_type, sigma_min=sigma_min, raw_sigma_bias=0.5, use_tilt=(config.bound == "fivo-aux")) else: raise ValueError("model flag: %s is unrecognized" % config.model) return inputs, targets, lengths, model, mean