def __init__(self, wrd_vocab, pos_vocab, non_vocab, config):
super(CMN, self).__init__()
self.config= config
self.dropout = self.config['dropout']
self.hdim = self.config['n_hidden']
self.wdim = self.config['word_dim']
self.feat_box = self.config['feat_box']
self.use_outer = self.config['use_outer']
self.fusion = self.config['fusion']
self.debug = self.config['debug']
self.evaluate = False
self.Wwrd = nn.Embedding(len(wrd_vocab), self.wdim)
self.w2i = wrd_vocab
self.SMAX = nn.Softmax()
self.LSMAX = nn.LogSoftmax()
self.SIGM = nn.Sigmoid()
self.RELU = nn.ReLU()
self.TANH = nn.Tanh()
self.DROP = nn.Dropout(self.dropout)
self.WscrSUB = nn.Linear(self.hdim*4, 1)
self.WscrOBJ = nn.Linear(self.hdim*4, 1)
self.WscrREL = nn.Linear(self.hdim*4, 1)
self.rnn0 = nn.LSTM(input_size = self.wdim ,hidden_size = self.hdim, num_layers = 1,bidirectional = True, dropout = self.dropout)
self.rnn1 = nn.LSTM(input_size = self.hdim*2,hidden_size = self.hdim, num_layers = 1,bidirectional = True, dropout = self.dropout, bias = False)
self.h00 = makevar(np.zeros((2,1,self.hdim)),numpy_var = True)
self.c00 = makevar(np.zeros((2,1,self.hdim)),numpy_var = True)
self.h01 = makevar(np.zeros((2,1,self.hdim)),numpy_var = True)
self.c01 = makevar(np.zeros((2,1,self.hdim)),numpy_var = True)
init_forget(self.rnn0)
init_forget(self.rnn1)
self.Wbox = nn.Linear(self.feat_box, self.wdim)
if self.fusion == 'concat':
# self.Wout0 = nn.Linear(2*self.wdim, self.wdim)
self.Wout0 = nn.Linear(2*self.wdim, 1)
# self.Wrel0 = nn.Linear(2*self.wdim, self.wdim)
else:
# self.Wout0 = nn.Linear(self.wdim, self.wdim)
self.Wout0 = nn.Linear(self.wdim, 1)
# self.Wrel0 = nn.Linear(self.wdim, self.hdim)
# self.Wout1 = nn.Linear(self.wdim, 1)
# if self.use_outer:
# self.Wrbox= nn.Linear(self.feat_box*2 + ((5+1)**2), self.wdim)
# else:
# self.Wrbox= nn.Linear(self.feat_box*2, self.wdim)
self.Wrbox= nn.Linear(5*2, self.wdim)
self.Wrel1 = nn.Linear(self.wdim, 1)
def __init__(self, wrd_vocab, pos_vocab, non_vocab, config):
super(BOX_MLP, self).__init__()
self.config = config
self.dropout = self.config['dropout']
self.hdim = self.config['n_hidden']
self.wdim = self.config['word_dim']
self.feat_box = self.config['feat_box']
self.n_layer = self.config['n_layer']
self.use_outer = self.config['use_outer']
self.fusion = self.config['fusion']
self.debug = self.config['debug']
self.evaluate = False
self.Wwrd = nn.Embedding(len(wrd_vocab), self.wdim)
self.w2i = wrd_vocab
self.SMAX = nn.Softmax()
self.SIGM = nn.Sigmoid()
self.RELU = nn.ReLU()
self.TANH = nn.Tanh()
self.DROP = nn.Dropout(self.dropout)
self.WscrSUB = nn.Linear(self.hdim * 4, 1)
self.rnn0 = nn.LSTM(input_size=self.wdim,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout)
self.rnn1 = nn.LSTM(input_size=self.hdim * 2,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout,
bias=False)
init_forget(self.rnn0)
init_forget(self.rnn1)
self.Wbox = nn.Linear(self.feat_box, self.wdim)
mlist = []
for i in range(self.n_layer):
if i == 0:
mlist.append(nn.Linear(self.feat_box + self.wdim, self.hdim))
elif i == self.n_layer - 1:
mlist.append(nn.Linear(self.hdim, 1))
else:
mlist.append(nn.Linear(self.hdim, self.hdim))
self.Wff = nn.ModuleList(mlist)
def __init__(self, wrd_vocab, pos_vocab, non_vocab, config, cnn_feat=4096):
super(CMN_LOC, self).__init__()
self.config = config
self.dropout = self.config['dropout']
self.hdim = self.config['n_hidden']
self.wdim = self.config['word_dim']
self.feat_box = self.config['feat_box']
self.cnn_feat = cnn_feat
self.use_outer = self.config['use_outer']
self.fusion = self.config['fusion']
self.debug = self.config['debug']
self.evaluate = False
self.Wwrd = nn.Embedding(len(wrd_vocab), self.wdim)
self.w2i = wrd_vocab
self.SMAX = nn.Softmax()
self.LSMAX = nn.LogSoftmax()
self.SIGM = nn.Sigmoid()
self.RELU = nn.ReLU()
self.TANH = nn.Tanh()
self.DROP = nn.Dropout(self.dropout)
self.WscrSUB = nn.Linear(self.hdim * 4, 1)
self.rnn0 = nn.LSTM(input_size=self.wdim,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout)
self.rnn1 = nn.LSTM(input_size=self.hdim * 2,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout,
bias=False)
init_forget(self.rnn0)
init_forget(self.rnn1)
if self.use_outer:
self.Wbox = nn.Linear(
(self.feat_box - self.cnn_feat + 1)**2 + self.feat_box,
self.wdim)
else:
self.Wbox = nn.Linear(self.feat_box, self.wdim)
self.Wout0 = nn.Linear(self.wdim, 1)
def __init__(self, wrd_vocab, pos_vocab, non_vocab, config):
super(GroundNET, self).__init__()
self.config = config
self.dropout = self.config['dropout']
self.hdim = self.config['n_hidden']
self.layer = self.config['n_layer']
self.wdim = self.config['word_dim']
self.feat_box = self.config['feat_box']
self.use_outer = self.config['use_outer']
self.fusion = self.config['fusion']
self.debug = self.config['debug']
self.encoder = self.config['encoder']
self.only_spatial = self.config['only_spatial']
self.Wwrd = nn.Embedding(len(wrd_vocab), self.wdim)
self.w2i = wrd_vocab
self.Wbox = nn.Linear(self.feat_box, self.wdim)
if self.use_outer:
if self.only_spatial:
self.Wrbox = nn.Linear(5 * 2 + ((5 + 1)**2), self.wdim)
else:
self.Wrbox = nn.Linear(self.feat_box * 2 + ((5 + 1)**2),
self.wdim)
else:
if self.only_spatial:
self.Wrbox = nn.Linear(5 * 2, self.wdim)
else:
self.Wrbox = nn.Linear(self.feat_box * 2, self.wdim)
self.SMAX = nn.Softmax()
self.LSMAX = nn.LogSoftmax()
self.SIGM = nn.Sigmoid()
self.RELU = nn.ReLU()
self.TANH = nn.Tanh()
self.DROP = nn.Dropout(self.dropout)
self.WDROP = WordDropout(self.dropout)
if self.fusion == 'concat':
out0_dim = self.wdim * 2
else:
out0_dim = self.wdim
if self.layer == 1 and self.fusion == 'concat':
out1_dim = self.wdim * 2
else:
out1_dim = self.wdim
self.Wrel0 = nn.Linear(out0_dim, self.wdim)
self.Wrel1 = nn.Linear(out1_dim, 1)
self.Wout0 = nn.Linear(out0_dim, self.wdim)
self.Wout1 = nn.Linear(out1_dim, 1)
self.Wscr = nn.Linear(self.hdim * 4, 1)
if self.encoder == "lstm":
self.rnn0 = nn.LSTM(input_size=self.wdim,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout)
self.rnn1 = nn.LSTM(input_size=self.hdim * 2,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout,
bias=False)
init_forget(self.rnn0)
init_forget(self.rnn1)
elif self.encoder == "gru":
self.rnn0 = nn.GRU(input_size=self.wdim,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout)
self.rnn1 = nn.GRU(input_size=self.hdim * 2,
hidden_size=self.hdim,
num_layers=1,
bidirectional=True,
dropout=self.dropout)
else:
raise NotImplementedError()
self.h00 = makevar(np.zeros((2, 1, self.hdim)), numpy_var=True)
self.c00 = makevar(np.zeros((2, 1, self.hdim)), numpy_var=True)
self.h01 = makevar(np.zeros((2, 1, self.hdim)), numpy_var=True)
self.c01 = makevar(np.zeros((2, 1, self.hdim)), numpy_var=True)