9:　l0 = F.linear(1, units),

9:　embed = F.EmbedID(n_vocab, n_units),

29:　h0 = F.relu(self.l0(x))

29:　h0 = self.embed(x)

66:　volatile = not train)

66:　volatile = not train) for name in ('c1', 'h1', 'c2', 'h2', 'c3', 'h3','c4','h4','c5','h5')}

15: def load_data(args):
16:     vocab = {}
17:     print ('%s/input.txt'% args.data_dir)
18:     # words = codecs.open('%s/input.txt' % args.data_dir, 'rb','UTF-8').read()
19: 
20:     dat = []
21:     for l in open('%s/input.txt' % args.data_dir).readlines():
22:         data = eval(l[:-1])
23:         dat.append(data)
24: 
25:     words = dat
26:     dataset = np.ndarray((1,1), dtype=np.float32)
27:     for i, word in enumerate(words):
28:         if word not in vocab:
29:             vocab[word] = len(vocab)
30:         dataset[i] = word
31:     print 'corpus length:', len(words)
32:     print 'vocab size:', len(vocab)
33:     return dataset, words, vocab

15: def load_data(args):
16:     vocab = {}
17:     print ('%s/input.txt'% args.data_dir)
18:     words = codecs.open('%s/input.txt' % args.data_dir, 'rb','UTF-8').read()
19:     words = list(words)
20:     dataset = np.ndarray((len(words),), dtype=np.int32)
21:     for i, word in enumerate(words):
22:         if word not in vocab:
23:             vocab[word] = len(vocab)
24:         dataset[i] = vocab[word]
25:     print 'corpus length:', len(words)
26:     print 'vocab size:', len(vocab)
27:     return dataset, words, vocab