def __init__(self, env, listener, tok):
self.env = env
self.feature_size = self.env.feature_size
self.tok = tok
self.tok.finalize()
self.listener = listener
# Model
print("VOCAB_SIZE", self.tok.vocab_size())
self.encoder = model.SpeakerEncoder(self.feature_size +
args.angle_feat_size,
args.rnn_dim,
args.dropout,
bidirectional=args.bidir).cuda()
self.decoder = model.SpeakerDecoder(self.tok.vocab_size(), args.wemb,
self.tok.word_to_index['<PAD>'],
args.rnn_dim, args.dropout).cuda()
self.encoder_optimizer = args.optimizer(self.encoder.parameters(),
lr=args.lr)
self.decoder_optimizer = args.optimizer(self.decoder.parameters(),
lr=args.lr)
# Evaluation
self.softmax_loss = torch.nn.CrossEntropyLoss(
ignore_index=self.tok.word_to_index['<PAD>'])
# Will be used in beam search
self.nonreduced_softmax_loss = torch.nn.CrossEntropyLoss(
ignore_index=self.tok.word_to_index['<PAD>'],
size_average=False,
reduce=False)
def __init__(self, env, listener, tok):
self.env = env
self.feature_size = self.env.feature_size
self.tok = tok
self.tok.finalize()
self.listener = listener
# Model
self.glove_dim = 300
with open(
'/students/u5399302/MatterportData/data/obj_stats2/objectvocab_filtered_dyno4.txt',
'r') as f_ov:
self.obj_vocab = [k.strip() for k in f_ov.readlines()]
glove_matrix = utils.get_glove_matrix(self.obj_vocab, self.glove_dim)
self.objencoder = ObjEncoder(glove_matrix.size(0),
glove_matrix.size(1),
glove_matrix).cuda()
print("VOCAB_SIZE", self.tok.vocab_size())
self.encoder = model.SpeakerEncoder(self.feature_size +
args.angle_feat_size,
args.rnn_dim,
args.dropout,
bidirectional=args.bidir).cuda()
self.decoder = model.SpeakerDecoder(self.tok.vocab_size(), args.wemb,
self.tok.word_to_index['<PAD>'],
args.rnn_dim, args.dropout).cuda()
self.encoder_optimizer = args.optimizer(self.encoder.parameters(),
lr=args.lr)
self.decoder_optimizer = args.optimizer(self.decoder.parameters(),
lr=args.lr)
# Evaluation
self.softmax_loss = torch.nn.CrossEntropyLoss(
ignore_index=self.tok.word_to_index['<PAD>'])
# Will be used in beam search
self.nonreduced_softmax_loss = torch.nn.CrossEntropyLoss(
ignore_index=self.tok.word_to_index['<PAD>'],
size_average=False,
reduce=False)
