net.eval()
# load parse generator network
parse_args = parse_model['config_args']
parse_net = ParseNet(parse_args.d_nt, parse_args.d_hid, len(parse_gen_voc))
if args.gpu >= 0:
parse_net.cuda()
parse_net.load_state_dict(parse_model['state_dict'])
parse_net.eval()
# encode templates
template_lens = [len(x.split()) for x in templates]
np_templates = np.zeros((len(templates), max(template_lens)), dtype='int32')
for z, template in enumerate(templates):
np_templates[z, :template_lens[z]] = [parse_gen_voc[w] for w in templates[z].split()]
if args.gpu >= 0:
tp_templates = Variable(torch.from_numpy(np_templates).long().cuda())
tp_template_lens = torch.from_numpy(np.array(template_lens, dtype='int32')).long().cuda()
else:
tp_templates = Variable(torch.from_numpy(np_templates).long())
tp_template_lens = torch.from_numpy(np.array(template_lens, dtype='int32')).long()
# instantiate BPE segmenter
bpe_codes = codecs.open(args.bpe_codes, encoding='utf-8')
bpe_vocab = codecs.open(args.bpe_vocab, encoding='utf-8')
bpe_vocab = read_vocabulary(bpe_vocab, args.bpe_vocab_thresh)
bpe = BPE(bpe_codes, '@@', bpe_vocab, None)
# paraphrase the sst!
encode_data(out_file=args.out_file)
parse_net.eval()
# encode templates
template_lens = [len(x.split()) for x in templates]
np_templates = np.zeros((len(templates), max(template_lens)), dtype='int32')
for z, template in enumerate(templates):
np_templates[z, :template_lens[z]] = [
parse_gen_voc[w] for w in templates[z].split()
]
tp_templates = Variable(torch.from_numpy(np_templates).long().cuda())
tp_template_lens = torch.from_numpy(np.array(template_lens,
dtype='int32')).long().cuda()
# instantiate BPE segmenter
bpe_codes = codecs.open(bpe_codes, encoding='utf-8')
bpe_vocab = codecs.open(bpe_vocab, encoding='utf-8')
bpe_vocab = read_vocabulary(bpe_vocab, bpe_vocab_thresh)
bpe = BPE(bpe_codes, '@@', bpe_vocab, None)
def reverse_bpe(sent):
x = []
cache = ''
for w in sent:
if w.endswith('@@'):
cache += w.replace('@@', '')
elif cache != '':
x.append(cache + w)
cache = ''
else:
x.append(w)
