def __init__(self, opt):
super(MoreSupWeightModel, self).__init__()
self.vocab_size = opt.vocab_size
self.input_encoding_size = opt.input_encoding_size
self.rnn_type = opt.rnn_type
self.rnn_size = opt.rnn_size
self.num_layers = opt.num_layers
self.drop_prob_lm = opt.drop_prob_lm
self.seq_length = opt.seq_length
self.fc_feat_size = opt.fc_feat_size
self.att_feat_size = opt.att_feat_size
self.att_size = opt.att_size
self.batch_size = opt.batch_size * opt.seq_per_img
self.rnn_atten = opt.rnn_atten
self.num_parallels = opt.num_parallels
self.sample_rate = opt.sample_rate
self.use_linear = opt.use_linear
self.rnn_size_list = opt.rnn_size_list
self.gram_num = opt.gram_num
self.logprob_pool_type = opt.logprob_pool_type # 0 mean 1 max
# reviewnet
self.use_reviewnet = opt.use_reviewnet
if self.use_reviewnet == 1:
self.review_length = opt.review_length
self.review_nets = nn.ModuleList()
for i in range(self.review_length):
self.review_nets[i] = LSTM.LSTM_SOFT_ATT_NOX(self.rnn_size, self.att_size, self.drop_prob_lm)
opt.att_size = self.review_length
# LSTM
# opt.input_encoding_size = opt.input_encoding_size * 2
self.core = rnn_utils.get_lstm(opt)
if self.rnn_atten == "ATT_LSTM":
self.atten = LSTM.LSTM_ATTEN_LAYER(self.rnn_size)
# self.vocab_size + 1 -> self.input_encoding_size
# self.vocab_size + 1 -> self.input_encoding_size
if self.gram_num > 0:
self.embed = nn.Sequential(nn.Embedding(self.vocab_size + 1, self.input_encoding_size),
Embed.WordEmbed(self.gram_num))
# self.embed_tc = nn.Sequential(nn.Embedding(self.vocab_size + 1, self.input_encoding_size),
# Embed.WordEmbed(self.gram_num))
# self.embed = nn.Embedding(self.vocab_size + 1, self.input_encoding_size)
# self.embed_tc = nn.Embedding(self.vocab_size + 1, self.input_encoding_size)
else:
self.embed = nn.Embedding(self.vocab_size + 1, self.input_encoding_size)
self.embed_tc = nn.Embedding(self.vocab_size + 1, self.input_encoding_size)
if self.use_linear:
# (batch_size * fc_feat_size) -> (batch_size * input_encoding_size)
self.img_embed = nn.Linear(self.fc_feat_size, self.input_encoding_size)
self.att_embed = nn.Linear(self.att_feat_size, self.input_encoding_size)
# self.relu = nn.RReLU(inplace=True)
self.relu = nn.ReLU()
self.init_weight()
def __init__(self, opt):
super(SCSTModel, self).__init__()
self.vocab_size = opt.vocab_size
self.input_encoding_size = opt.input_encoding_size
self.rnn_type = opt.rnn_type
self.rnn_size = opt.rnn_size
self.num_layers = opt.num_layers
self.drop_prob_lm = opt.drop_prob_lm
self.seq_length = opt.seq_length
self.fc_feat_size = opt.fc_feat_size
self.att_feat_size = opt.att_feat_size
self.att_size = opt.att_size
self.batch_size = opt.batch_size * opt.seq_per_img
self.rnn_atten = opt.rnn_atten
# LSTM
if self.rnn_atten == "ATT_LSTM":
self.atten = LSTM.LSTM_ATTEN_LAYER(self.rnn_size)
# LSTM
if self.rnn_type == "LSTM":
self.core = LSTM.LSTM(self.input_encoding_size * 2,
self.vocab_size + 1,
self.rnn_size,
dropout=self.drop_prob_lm)
elif self.rnn_type == "LSTM_SOFT_ATT":
self.core = LSTM.LSTM_SOFT_ATT(self.input_encoding_size * 2,
self.vocab_size + 1,
self.rnn_size,
self.att_size,
dropout=self.drop_prob_lm)
elif self.rnn_type == "LSTM_DOUBLE_ATT":
self.core = LSTM.LSTM_DOUBLE_ATT(self.input_encoding_size * 2,
self.vocab_size + 1,
self.rnn_size,
self.att_size,
dropout=self.drop_prob_lm)
# self.vocab_size + 1 -> self.input_encoding_size
self.embed = nn.Embedding(self.vocab_size + 1,
self.input_encoding_size)
self.embed_tc = nn.Embedding(self.vocab_size + 1,
self.input_encoding_size)
# (batch_size * fc_feat_size) -> (batch_size * input_encoding_size)
self.img_embed = nn.Linear(self.fc_feat_size, self.input_encoding_size)
self.att_embed = nn.Linear(self.att_feat_size,
self.input_encoding_size)
self.init_weights()
def __init__(self, opt):
super(DoubleAttenMModel, self).__init__()
self.vocab_size = opt.vocab_size
self.input_encoding_size = opt.input_encoding_size
self.rnn_type = opt.rnn_type
self.rnn_size = opt.rnn_size
self.num_layers = opt.num_layers
self.drop_prob_lm = opt.drop_prob_lm
self.seq_length = opt.seq_length
self.fc_feat_size = opt.fc_feat_size
self.att_feat_size = opt.att_feat_size
self.att_size = opt.att_size
self.batch_size = opt.batch_size * opt.seq_per_img
self.rnn_atten = opt.rnn_atten
self.num_layers = opt.num_layers
self.num_parallels = opt.num_parallels
self.sample_rate = opt.sample_rate
self.use_linear = opt.use_linear
self.rnn_size_list = opt.rnn_size_list
# reviewnet
self.use_reviewnet = opt.use_reviewnet
if self.use_reviewnet == 1:
self.review_length = opt.review_length
self.review_nets = nn.ModuleList()
for i in range(self.review_length):
self.review_nets[i] = LSTM.LSTM_SOFT_ATT_NOX(
self.rnn_size, self.att_size, self.drop_prob_lm)
opt.att_size = self.review_length
# LSTM
self.core = rnn_utils.get_lstm(opt)
if self.rnn_atten == "ATT_LSTM":
self.atten = LSTM.LSTM_ATTEN_LAYER(self.rnn_size)
# self.vocab_size + 1 -> self.input_encoding_size
self.embed = nn.Embedding(self.vocab_size + 1,
self.input_encoding_size)
# self.embed_tc = nn.Embedding(self.vocab_size + 1, self.input_encoding_size)
if self.use_linear:
# (batch_size * fc_feat_size) -> (batch_size * input_encoding_size)
self.img_embed = nn.Linear(self.fc_feat_size, self.rnn_size)
self.att_embed = nn.Linear(self.att_feat_size, self.rnn_size)
# self.relu = nn.RReLU(inplace=True)
self.relu = nn.ReLU()
self.init_weight()