def __init__(self, config):
super(HRED, self).__init__()
self.config = config
self.encoder = layers.EncoderRNN(config.vocab_size,
config.embedding_size,
config.encoder_hidden_size,
config.rnn,
config.num_layers,
config.bidirectional,
config.dropout)
context_input_size = (config.num_layers
* config.encoder_hidden_size
* self.encoder.num_directions)
if config.context_input_only:
context_input_size += (config.emo_output_size \
+ config.infersent_output_size)
self.context_encoder = layers.ContextRNN(context_input_size,
config.context_size,
config.rnn,
config.num_layers,
config.dropout)
self.decoder = layers.DecoderRNN(config.vocab_size,
config.embedding_size,
config.decoder_hidden_size,
config.rnncell,
config.num_layers,
config.dropout,
config.word_drop,
config.max_unroll,
config.sample,
config.temperature,
config.beam_size)
self.context2decoder = layers.FeedForward(config.context_size,
config.num_layers * config.decoder_hidden_size,
num_layers=1,
activation=config.activation)
if config.tie_embedding:
self.decoder.embedding = self.encoder.embedding
if config.emotion:
self.context2emoji = layers.FeedForward(
config.context_size, config.emo_output_size,
num_layers=config.emo_num_layers,
hidden_size=config.emo_embedding_size,
activation=config.emo_activation)
if config.infersent:
self.context2infersent = layers.FeedForward(
config.context_size, config.infersent_output_size,
num_layers=config.infersent_num_layers,
hidden_size=config.infersent_embedding_size,
activation=config.infersent_activation,
no_activation_last_layer=True)
def __init__(self, config):
super(VHCR, self).__init__()
self.config = config
self.encoder = layers.EncoderRNN(config.vocab_size,
config.embedding_size,
config.encoder_hidden_size,
config.rnn,
config.num_layers,
config.bidirectional,
config.dropout)
context_inference_size = (config.num_layers
* config.encoder_hidden_size
* self.encoder.num_directions)
posterior_input_size = (config.num_layers
* config.encoder_hidden_size
* self.encoder.num_directions
+ config.context_size
+ config.z_conv_size)
if config.context_input_only:
context_inference_size += (config.emo_output_size
+ config.infersent_output_size)
posterior_input_size += (config.emo_output_size
+ config.infersent_output_size)
context_encoder_size = context_inference_size + config.z_conv_size
self.context_encoder = layers.ContextRNN(context_encoder_size,
config.context_size,
config.rnn,
config.num_layers,
config.dropout)
self.unk_sent = nn.Parameter(torch.randn(context_encoder_size - config.z_conv_size))
self.z_conv2context = layers.FeedForward(config.z_conv_size,
config.num_layers * config.context_size,
num_layers=1,
activation=config.activation)
self.context_inference = layers.ContextRNN(context_inference_size,
config.context_size,
config.rnn,
config.num_layers,
config.dropout,
bidirectional=True)
self.decoder = layers.DecoderRNN(config.vocab_size,
config.embedding_size,
config.decoder_hidden_size,
config.rnncell,
config.num_layers,
config.dropout,
config.word_drop,
config.max_unroll,
config.sample,
config.temperature,
config.beam_size)
self.context2decoder = layers.FeedForward(
config.context_size + config.z_sent_size + config.z_conv_size,
config.num_layers * config.decoder_hidden_size,
num_layers=1,
activation=config.activation)
self.softplus = nn.Softplus()
self.conv_posterior_h = layers.FeedForward(
config.num_layers * self.context_inference.num_directions * config.context_size,
config.context_size,
num_layers=2,
hidden_size=config.context_size,
activation=config.activation)
self.conv_posterior_mu = nn.Linear(config.context_size,
config.z_conv_size)
self.conv_posterior_var = nn.Linear(config.context_size,
config.z_conv_size)
self.sent_prior_h = layers.FeedForward(config.context_size + config.z_conv_size,
config.context_size,
num_layers=1,
hidden_size=config.z_sent_size,
activation=config.activation)
self.sent_prior_mu = nn.Linear(config.context_size,
config.z_sent_size)
self.sent_prior_var = nn.Linear(config.context_size,
config.z_sent_size)
self.sent_posterior_h = layers.FeedForward(
posterior_input_size,
config.context_size,
num_layers=2,
hidden_size=config.context_size,
activation=config.activation)
self.sent_posterior_mu = nn.Linear(config.context_size,
config.z_sent_size)
self.sent_posterior_var = nn.Linear(config.context_size,
config.z_sent_size)
if config.tie_embedding:
self.decoder.embedding = self.encoder.embedding
if config.emotion:
self.context2emoji = layers.FeedForward(
config.context_size, config.emo_output_size,
num_layers=config.emo_num_layers,
hidden_size=config.emo_embedding_size,
activation=config.emo_activation)
if config.infersent:
self.context2infersent = layers.FeedForward(
config.context_size, config.infersent_output_size,
num_layers=config.infersent_num_layers,
hidden_size=config.infersent_embedding_size,
activation=config.infersent_activation,
no_activation_last_layer=True)