def main(args):
options, ckpt_file = load_options_latest_checkpoint(args.save_dir)
if 'char_cnn' in options:
max_word_length = options['char_cnn']['max_characters_per_token']
else:
max_word_length = None
vocab = load_vocab(args.vocab_file, max_word_length)
prefix = args.train_prefix
kwargs = {
'test': False,
'shuffle_on_load': True,
}
if options.get('bidirectional'):
data = BidirectionalLMDataset(prefix, vocab, **kwargs)
else:
data = LMDataset(prefix, vocab, **kwargs)
tf_save_dir = args.save_dir
tf_log_dir = args.save_dir
# set optional inputs
if args.n_train_tokens > 0:
options['n_train_tokens'] = args.n_train_tokens
if args.n_epochs > 0:
options['n_epochs'] = args.n_epochs
if args.batch_size > 0:
options['batch_size'] = args.batch_size
train(options, data, args.n_gpus, tf_save_dir, tf_log_dir,
restart_ckpt_file=ckpt_file)
def test_train_bilm_chars(self):
vocab, data, options = self._get_vocab_data_options(True, True)
train(options, data, 1, self.tmp_dir, self.tmp_dir)
# now test
tf.reset_default_graph()
options, ckpt_file = load_options_latest_checkpoint(self.tmp_dir)
data_test, vocab_test = self._get_data(True, True, True)
perplexity = test(options, ckpt_file, data_test, batch_size=1)
self.assertTrue(perplexity < 20.0)
def test_train_skip_connections(self):
bidirectional = True
use_chars = False
vocab, data, options = self._get_vocab_data_options(
bidirectional, use_chars)
options['lstm']['use_skip_connections'] = True
train(options, data, 1, self.tmp_dir, self.tmp_dir)
# now test
tf.reset_default_graph()
options, ckpt_file = load_options_latest_checkpoint(self.tmp_dir)
data_test, vocab_test = self._get_data(
bidirectional, use_chars, test=True)
perplexity = test(options, ckpt_file, data_test, batch_size=1)
self.assertTrue(perplexity < 20.0)
def test_train_shared_softmax_embedding(self):
bidirectional = True
use_chars = False
vocab, data, options = self._get_vocab_data_options(
bidirectional, use_chars, share_embedding_softmax=True)
train(options, data, 1, self.tmp_dir, self.tmp_dir)
# now test
tf.reset_default_graph()
options, ckpt_file = load_options_latest_checkpoint(self.tmp_dir)
data_test, vocab_test = self._get_data(
bidirectional, use_chars, test=True)
perplexity = test(options, ckpt_file, data_test, batch_size=1)
self.assertTrue(perplexity < 20.0)
def main(args):
options, ckpt_file = load_options_latest_checkpoint(args.save_dir)
# load the vocab
if 'char_cnn' in options:
max_word_length = options['char_cnn']['max_characters_per_token']
else:
max_word_length = None
vocab = load_vocab(args.vocab_file, max_word_length)
test_prefix = args.test_prefix
kwargs = {
'test': True,
'shuffle_on_load': False,
}
if options.get('bidirectional'):
data = BidirectionalLMDataset(test_prefix, vocab, **kwargs)
else:
data = LMDataset(test_prefix, vocab, **kwargs)
test(options, ckpt_file, data, batch_size=args.batch_size)