def get_dev_streams(config):
"""Setup development set stream if necessary."""
dev_streams = {}
for cg in config['cgs']:
if 'val_sets' in config and cg in config['val_sets']:
logger.info('Building development stream for cg:[{}]'.format(cg))
eid = p_(cg)[0]
dev_file = config['val_sets'][cg]
# Get dictionary and fix EOS
dictionary = cPickle.load(open(config['src_vocabs'][eid]))
dictionary['<S>'] = 0
dictionary['<UNK>'] = config['unk_id']
dictionary['</S>'] = config['src_eos_idxs'][eid]
# Get as a text file and convert it into a stream
dev_dataset = TextFile([dev_file], dictionary, None)
dev_streams[cg] = DataStream(dev_dataset)
return dev_streams
评论列表
文章目录