def __init__(self, corpus, config): super(HRED, self).__init__(config) self.vocab = corpus.vocab self.vocab_dict = corpus.vocab_dict self.vocab_size = len(self.vocab) self.goal_vocab = corpus.goal_vocab self.goal_vocab_dict = corpus.goal_vocab_dict self.goal_vocab_size = len(self.goal_vocab) self.outcome_vocab = corpus.outcome_vocab self.outcome_vocab_dict = corpus.outcome_vocab_dict self.outcome_vocab_size = len(self.outcome_vocab) self.sys_id = self.vocab_dict[SYS] self.eos_id = self.vocab_dict[EOS] self.pad_id = self.vocab_dict[PAD] self.goal_encoder = MlpGoalEncoder(goal_vocab_size=self.goal_vocab_size, k=config.k, nembed=config.goal_embed_size, nhid=config.goal_nhid, init_range=config.init_range) self.embedding = nn.Embedding(self.vocab_size, config.embed_size, padding_idx=self.pad_id) self.utt_encoder = RnnUttEncoder(vocab_size=self.vocab_size, embedding_dim=config.embed_size, feat_size=1, goal_nhid=config.goal_nhid, rnn_cell=config.utt_rnn_cell, utt_cell_size=config.utt_cell_size, num_layers=config.num_layers, input_dropout_p=config.dropout, output_dropout_p=config.dropout, bidirectional=config.bi_utt_cell, variable_lengths=False, use_attn=config.enc_use_attn, embedding=self.embedding) self.ctx_encoder = EncoderRNN(input_dropout_p=0.0, rnn_cell=config.ctx_rnn_cell, # input_size=self.utt_encoder.output_size+config.goal_nhid, input_size=self.utt_encoder.output_size, hidden_size=config.ctx_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=config.bi_ctx_cell, variable_lengths=False) # TODO connector if config.bi_ctx_cell: self.connector = Bi2UniConnector(rnn_cell=config.ctx_rnn_cell, num_layer=1, hidden_size=config.ctx_cell_size, output_size=config.dec_cell_size) else: self.connector = IdentityConnector() self.decoder = DecoderRNN(input_dropout_p=config.dropout, rnn_cell=config.dec_rnn_cell, input_size=config.embed_size + config.goal_nhid, hidden_size=config.dec_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=False, vocab_size=self.vocab_size, use_attn=config.dec_use_attn, ctx_cell_size=self.ctx_encoder.output_size, attn_mode=config.dec_attn_mode, sys_id=self.sys_id, eos_id=self.eos_id, use_gpu=config.use_gpu, max_dec_len=config.max_dec_len, embedding=self.embedding) self.nll = NLLEntropy(self.pad_id, config.avg_type)
def __init__(self, corpus, config): super(HRED, self).__init__(config) self.vocab = corpus.vocab self.vocab_dict = corpus.vocab_dict self.vocab_size = len(self.vocab) self.goal_vocab = corpus.goal_vocab self.goal_vocab_dict = corpus.goal_vocab_dict self.goal_vocab_size = len(self.goal_vocab) self.outcome_vocab = corpus.outcome_vocab self.outcome_vocab_dict = corpus.outcome_vocab_dict self.outcome_vocab_size = len(self.outcome_vocab) self.sys_id = self.vocab_dict[SYS] self.eos_id = self.vocab_dict[EOS] self.pad_id = self.vocab_dict[PAD] self.goal_encoder = MlpGoalEncoder( goal_vocab_size=self.goal_vocab_size, k=config.k, nembed=config.goal_embed_size, nhid=config.goal_nhid, init_range=config.init_range) self.embedding = nn.Embedding(self.vocab_size, config.embed_size, padding_idx=self.pad_id) self.utt_encoder = RnnUttEncoder(vocab_size=self.vocab_size, embedding_dim=config.embed_size, feat_size=1, goal_nhid=config.goal_nhid, rnn_cell=config.utt_rnn_cell, utt_cell_size=config.utt_cell_size, num_layers=config.num_layers, input_dropout_p=config.dropout, output_dropout_p=config.dropout, bidirectional=config.bi_utt_cell, variable_lengths=False, use_attn=config.enc_use_attn, embedding=self.embedding) self.ctx_encoder = EncoderRNN( input_dropout_p=0.0, rnn_cell=config.ctx_rnn_cell, # input_size=self.utt_encoder.output_size+config.goal_nhid, input_size=self.utt_encoder.output_size, hidden_size=config.ctx_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=config.bi_ctx_cell, variable_lengths=False) # TODO connector if config.bi_ctx_cell: self.connector = Bi2UniConnector(rnn_cell=config.ctx_rnn_cell, num_layer=1, hidden_size=config.ctx_cell_size, output_size=config.dec_cell_size) else: self.connector = IdentityConnector() self.decoder = DecoderRNN(input_dropout_p=config.dropout, rnn_cell=config.dec_rnn_cell, input_size=config.embed_size + 2 * config.goal_nhid, hidden_size=config.dec_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=False, vocab_size=self.vocab_size, use_attn=config.dec_use_attn, ctx_cell_size=self.ctx_encoder.output_size, attn_mode=config.dec_attn_mode, sys_id=self.sys_id, eos_id=self.eos_id, use_gpu=config.use_gpu, max_dec_len=config.max_dec_len, embedding=self.embedding) self.nll = NLLEntropy(self.pad_id, config.avg_type) self.out_backward_size = config.out_backward_size self.z_size = config.z_size self.z_dim = config.z_dim self.z_emb = nn.Parameter(th.FloatTensor(config.z_size, config.z_dim)) # oracle modules self.book_emb = nn.Embedding(16, 32) self.hat_emb = nn.Embedding(16, 32) self.ball_emb = nn.Embedding(16, 32) self.res_layer = nn_lib.ResidualLayer(3 * 32, 128) self.book_emb_out = nn.Embedding(16, 32) self.hat_emb_out = nn.Embedding(16, 32) self.ball_emb_out = nn.Embedding(16, 32) self.res_layer_out = nn_lib.ResidualLayer(3 * 32, 128) self.prop_utt_encoder = RnnUttEncoder( vocab_size=self.vocab_size, embedding_dim=config.embed_size, feat_size=1, goal_nhid=config.goal_nhid, rnn_cell=config.utt_rnn_cell, utt_cell_size=config.utt_cell_size, num_layers=config.num_layers, input_dropout_p=config.dropout, output_dropout_p=config.dropout, bidirectional=config.bi_utt_cell, variable_lengths=False, use_attn=config.enc_use_attn, embedding=self.embedding, ) self.prop_ctx_encoder = EncoderRNN( input_dropout_p=0.0, rnn_cell=config.ctx_rnn_cell, # input_size=self.utt_encoder.output_size+config.goal_nhid, input_size=self.utt_encoder.output_size + 64 if config.oracle_context else self.utt_encoder.output_size, hidden_size=config.ctx_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=config.bi_ctx_cell, variable_lengths=False, ) self.w_pz0 = nn.Linear(64, 64, bias=False) self.prior_res_layer = nn_lib.ResidualLayer(config.ctx_cell_size, 64) self.res_goal_mlp = nn_lib.ResidualLayer(256 + config.goal_nhid, 128)
def __init__(self, corpus, config): super(Hmm, self).__init__(config) self.vocab = corpus.vocab self.vocab_dict = corpus.vocab_dict self.vocab_size = len(self.vocab) self.goal_vocab = corpus.goal_vocab self.goal_vocab_dict = corpus.goal_vocab_dict self.goal_vocab_size = len(self.goal_vocab) self.outcome_vocab = corpus.outcome_vocab self.outcome_vocab_dict = corpus.outcome_vocab_dict self.outcome_vocab_size = len(self.outcome_vocab) self.sys_id = self.vocab_dict[SYS] self.eos_id = self.vocab_dict[EOS] self.pad_id = self.vocab_dict[PAD] self.goal_encoder = MlpGoalEncoder( goal_vocab_size=self.goal_vocab_size, k=config.k, nembed=config.goal_embed_size, nhid=config.goal_nhid, init_range=config.init_range) self.embedding = nn.Embedding(self.vocab_size, config.embed_size, padding_idx=self.pad_id) self.utt_encoder = RnnUttEncoder(vocab_size=self.vocab_size, embedding_dim=config.embed_size, feat_size=1, goal_nhid=config.goal_nhid, rnn_cell=config.utt_rnn_cell, utt_cell_size=config.utt_cell_size, num_layers=config.num_layers, input_dropout_p=config.dropout, output_dropout_p=config.dropout, bidirectional=config.bi_utt_cell, variable_lengths=False, use_attn=config.enc_use_attn, embedding=self.embedding) self.ctx_encoder = EncoderRNN( input_dropout_p=0.0, rnn_cell=config.ctx_rnn_cell, # input_size=self.utt_encoder.output_size+config.goal_nhid, input_size=self.utt_encoder.output_size, hidden_size=config.ctx_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=config.bi_ctx_cell, variable_lengths=False) # TODO connector if config.bi_ctx_cell: self.connector = Bi2UniConnector(rnn_cell=config.ctx_rnn_cell, num_layer=1, hidden_size=config.ctx_cell_size, output_size=config.dec_cell_size) else: self.connector = IdentityConnector() self.decoder = DecoderRNN(input_dropout_p=config.dropout, rnn_cell=config.dec_rnn_cell, input_size=config.embed_size + config.goal_nhid + 64, hidden_size=config.dec_cell_size, num_layers=config.num_layers, output_dropout_p=config.dropout, bidirectional=False, vocab_size=self.vocab_size, use_attn=config.dec_use_attn, ctx_cell_size=self.ctx_encoder.output_size, attn_mode=config.dec_attn_mode, sys_id=self.sys_id, eos_id=self.eos_id, use_gpu=config.use_gpu, max_dec_len=config.max_dec_len, embedding=self.embedding) self.nll = NLLEntropy(self.pad_id, config.avg_type) # new hmm stuff self.noisy_proposal_labels = config.noisy_proposal_labels self.z_size = config.z_size # for the transition matrix self.book_emb = nn.Embedding(16, 32) self.hat_emb = nn.Embedding(16, 32) self.ball_emb = nn.Embedding(16, 32) self.res_layer = nn_lib.ResidualLayer(3 * 32, 64) self.book_emb_out = nn.Embedding(16, 32) self.hat_emb_out = nn.Embedding(16, 32) self.ball_emb_out = nn.Embedding(16, 32) self.res_layer_out = nn_lib.ResidualLayer(3 * 32, 64) self.res_goal_mlp = nn_lib.ResidualLayer(64 * 3, 64 * 2) self.w_pz0 = nn.Linear(64, 64, bias=False) self.prior_res_layer = nn_lib.ResidualLayer(config.ctx_cell_size, 2 * 64)