gt4sd.frameworks.granular.ml.models.vae_rnn.core module

VaeRnn implementation.

Summary

Classes:

VaeRnn

VaeRnn - variational encoder using RNN with Gaussian prior and approximate posterior.

Reference

class VaeRnn(name, position, data, vocab_size, embedding_size, tokenizer, hidden_size_enc=265, n_layers_enc=2, hidden_size_dec=265, n_layers_dec=2, bidirectional=False, latent_size=196, teacher_forcing=True, loss_function='ce', kl_low=0.0, kl_high=0.1, kl_n_epochs=100, kl_start_epoch=0, inference_check_frequency=50, **kwargs)

Bases: GranularEncoderDecoderModel

VaeRnn - variational encoder using RNN with Gaussian prior and approximate posterior.

__init__(name, position, data, vocab_size, embedding_size, tokenizer, hidden_size_enc=265, n_layers_enc=2, hidden_size_dec=265, n_layers_dec=2, bidirectional=False, latent_size=196, teacher_forcing=True, loss_function='ce', kl_low=0.0, kl_high=0.1, kl_n_epochs=100, kl_start_epoch=0, inference_check_frequency=50, **kwargs)

Construct VaeRnn.

Parameters

• name (str) – model name.

• position (int) – position of the model.

• data (Dict[str, str]) – data name mappings.

• vocab_size (int) – size of the vocabulary.

• embedding_size (int) – size of the embedding vectors.

• tokenizer (Tokenizer) – tokenizer.

• hidden_size_enc (int) – encoder hidden size. Defaults to 256.

• n_layers_enc (int) – number of layers for the encoder. Defaults to 2.

• hidden_size_dec (int) – decoder hidden size. Defaults to 256.

• n_layers_dec (int) – number of layers for the decoder. Defaults to 2.

• bidirectional (bool) – whether the RNN cell is bidirectional. Defaults to False.

• latent_size (int) – latent size. Defaults to 196.

• teacher_forcing (bool) – whether to teacher forcing. Defaults to True.

• loss_function (str) – loss function. Defaults to “ce”.

• kl_low (float) – low KL weight. Defaults to 0.0.

• kl_high (float) – high KL weight. Defaults to 0.1.

• kl_n_epochs (int) – KL number of epochs. Defaults to 100.

• kl_start_epoch (int) – KL starting epoch. Defaults to 0.

• inference_check_frequency (int) – frequency for checking inference quality. Defaults to 50.

Raises

ValueError – in case the provided loss function is not supported.

decode(z, max_len=127, *args, **kwargs)

Decode a latent space point.

Parameters

• z (Any) – latent point.

• max_len (int) – maximum sequence length. Defaults to 127.

Return type

Any

Returns

tuple with decoded texts and token indices.

_sampling_step(x, *args, **kwargs)

Run a sampling step in the model.

Parameters

x (Any) – model input.

Return type

Any

Returns

model sampling step output.

encode(x, *args, **kwargs)

Encode a sample.

Parameters

x (Any) – input sample.

Return type

Any

Returns

latent encoding.

encode_decode(x, max_len=127, *args, **kwargs)

Encode and decode a sample.

Parameters

• x (Any) – input sample.

• max_len (int) – maximum sequence length. Defaults to 127.

Return type

Any

Returns

decoded sample.

inference(x, *args, **kwargs)

Run the model in inference mode.

Parameters

x (Any) – sample.

Return type

Any

Returns

generated output.

_run_step(x, *args, **kwargs)

Run a step in the model.

Parameters

x (Any) – model input.

Return type

Any

Returns

model step output.

step(input_data, target_data, device='cpu', current_epoch=0, *args, **kwargs)

Training step for the model.

Parameters

• input_data (Any) – input for the step.

• target_data (Any) – target for the step.

• device (str) – string representing the device to use. Defaults to “cpu”.

• current_epoch (int) – current epoch. Defaults to 0.

Return type

Tuple[Any, Any, Any]

Returns

a tuple containing the step output, the loss and the logs for the module.

val_step(input_data, target_data, device='cpu', current_epoch=0, *args, **kwargs)

Validation step for the model.

Parameters

• input_data (Any) – input for the step.

• target_data (Any) – target for the step.

• device (str) – string representing the device to use. Defaults to “cpu”.

• current_epoch (int) – current epoch. Defaults to 0.

Return type

Any

Returns

a tuple containing the step output, the loss and the logs for the module.

static add_model_specific_args(parent_parser, name, *args, **kwargs)

Adding to a parser model specific arguments.

Parameters

• parent_parser (ArgumentParser) – patent parser.

• name (str) – model name.

Return type

ArgumentParser

Returns

updated parser.

__annotations__ = {}

__doc__ = 'VaeRnn - variational encoder using RNN with Gaussian prior and approximate posterior.'

__module__ = 'gt4sd.frameworks.granular.ml.models.vae_rnn.core'