def sample(args):
numpy.random.seed(args.random_seed)
if args.debug:
theano.config.compute_test_value = 'warn'
else:
theano.config.compute_test_value = 'off'
with h5py.File(args.model_path, 'r') as state:
print("Reading vocabulary from network state.")
sys.stdout.flush()
vocabulary = Vocabulary.from_state(state)
print("Number of words in vocabulary:", vocabulary.num_words())
print("Number of word classes:", vocabulary.num_classes())
print("Building neural network.")
sys.stdout.flush()
architecture = Architecture.from_state(state)
network = Network(vocabulary,
architecture,
mode=Network.Mode(minibatch=False))
print("Restoring neural network state.")
network.set_state(state)
print("Building text sampler.")
sys.stdout.flush()
sampler = TextSampler(network)
sequences = sampler.generate(30, args.num_sentences)
for sequence in sequences:
try:
eos_pos = sequence.index('</s>')
sequence = sequence[:eos_pos + 1]
except:
pass
args.output_file.write(' '.join(sequence) + '\n')
def sample(args):
numpy.random.seed(args.random_seed)
if args.debug:
theano.config.compute_test_value = 'warn'
else:
theano.config.compute_test_value = 'off'
with h5py.File(args.model_path, 'r') as state:
print("Reading vocabulary from network state.")
sys.stdout.flush()
vocabulary = Vocabulary.from_state(state)
print("Number of words in vocabulary:", vocabulary.num_words())
print("Number of word classes:", vocabulary.num_classes())
print("Building neural network.")
sys.stdout.flush()
architecture = Architecture.from_state(state)
network = Network(vocabulary, architecture,
predict_next_distribution=True)
print("Restoring neural network state.")
network.set_state(state)
print("Building text sampler.")
sys.stdout.flush()
sampler = TextSampler(network)
for i in range(args.num_sentences):
words = sampler.generate()
args.output_file.write('{}: {}\n'.format(
i, ' '.join(words)))
def sample(args):
numpy.random.seed(args.random_seed)
if args.debug:
theano.config.compute_test_value = 'warn'
else:
theano.config.compute_test_value = 'off'
with h5py.File(args.model_path, 'r') as state:
print("Reading vocabulary from network state.")
sys.stdout.flush()
vocabulary = Vocabulary.from_state(state)
print("Number of words in vocabulary:", vocabulary.num_words())
print("Number of word classes:", vocabulary.num_classes())
print("Building neural network.")
sys.stdout.flush()
architecture = Architecture.from_state(state)
network = Network(architecture, vocabulary, mode=Network.Mode(minibatch=False))
print("Restoring neural network state.")
network.set_state(state)
print("Building text sampler.")
sys.stdout.flush()
sampler = TextSampler(network)
sequences = sampler.generate(30, args.num_sentences)
for sequence in sequences:
try:
eos_pos = sequence.index('</s>')
sequence = sequence[:eos_pos+1]
except:
pass
args.output_file.write(' '.join(sequence) + '\n')
def test_generate(self):
# Network predicts <unk> probability.
sampler = TextSampler(self.dummy_network)
words = sampler.generate(50, 10)
self.assertEqual(len(words), 10)
for sequence in words:
self.assertEqual(len(sequence), 50)
self.assertEqual(sequence[0], '<s>')
for left, right in zip(sequence, sequence[1:]):
if left == '<s>':
self.assertTrue(right == 'yksi' or right == 'kaksi')
elif left == 'yksi':
self.assertTrue(right == 'kaksi' or right == '</s>')
elif left == 'kaksi':
self.assertTrue(right == 'yksi' or right == '</s>')
elif left == '</s>':
self.assertEqual(right, '<s>')
def test_generate(self):
# Network predicts <unk> probability.
sampler = TextSampler(self.dummy_network)
words = sampler.generate(50, 10)
self.assertEqual(len(words), 10)
for sequence in words:
self.assertEqual(len(sequence), 50)
self.assertEqual(sequence[0], '<s>')
for left, right in zip(sequence, sequence[1:]):
if left == '<s>':
self.assertTrue(right == 'yksi' or right == 'kaksi')
elif left == 'yksi':
self.assertTrue(right == 'kaksi' or right == '</s>')
elif left == 'kaksi':
self.assertTrue(right == 'yksi' or right == '</s>')
elif left == '</s>':
self.assertEqual(right, '<s>')
def sample(args):
"""A function that performs the "theanolm sample" command.
:type args: argparse.Namespace
:param args: a collection of command line arguments
"""
numpy.random.seed(args.random_seed)
if args.debug:
theano.config.compute_test_value = 'warn'
else:
theano.config.compute_test_value = 'off'
with h5py.File(args.model_path, 'r') as state:
logging.info("Reading vocabulary from network state.")
vocabulary = Vocabulary.from_state(state)
logging.info("Number of words in vocabulary: %d",
vocabulary.num_words())
logging.info("Number of words in shortlist: %d",
vocabulary.num_shortlist_words())
logging.info("Number of word classes: %d", vocabulary.num_classes())
logging.info("Building neural network.")
architecture = Architecture.from_state(state)
default_device = get_default_device(args.default_device)
network = Network(architecture,
vocabulary,
mode=Network.Mode(minibatch=False),
default_device=default_device)
logging.info("Restoring neural network state.")
network.set_state(state)
logging.info("Building text sampler.")
sampler = TextSampler(network)
sequences = sampler.generate(args.sentence_length,
args.num_sentences,
seed_sequence=args.seed_sequence)
for sequence in sequences:
try:
eos_pos = sequence.index('</s>')
sequence = sequence[:eos_pos + 1]
except ValueError:
pass
args.output_file.write(' '.join(sequence) + '\n')
def __init__(self, model_path):
self.model_path = model_path
numpy.random.seed()
theano.config.compute_test_value = 'off'
with h5py.File(model_path, 'r') as self.state:
print("Reading vocabulary from network state.")
#sys.stdout.flush()
self.vocabulary = Vocabulary.from_state(self.state)
print("Number of words in vocabulary:", self.vocabulary.num_words())
print("Number of words in shortlist:", self.vocabulary.num_shortlist_words())
print("Number of word classes:", self.vocabulary.num_classes())
print("Building neural network.")
#sys.stdout.flush()
self.architecture = Architecture.from_state(self.state)
self.network = Network(self.architecture, self.vocabulary, mode=Network.Mode(minibatch=False))
print("Restoring neural network state.")
self.network.set_state(self.state)
print("Building text sampler.")
#sys.stdout.flush()
self.sampler = TextSampler(self.network)
class Sampler:
def __init__(self, model_path):
self.model_path = model_path
numpy.random.seed()
theano.config.compute_test_value = 'off'
with h5py.File(model_path, 'r') as self.state:
print("Reading vocabulary from network state.")
#sys.stdout.flush()
self.vocabulary = Vocabulary.from_state(self.state)
print("Number of words in vocabulary:", self.vocabulary.num_words())
print("Number of words in shortlist:", self.vocabulary.num_shortlist_words())
print("Number of word classes:", self.vocabulary.num_classes())
print("Building neural network.")
#sys.stdout.flush()
self.architecture = Architecture.from_state(self.state)
self.network = Network(self.architecture, self.vocabulary, mode=Network.Mode(minibatch=False))
print("Restoring neural network state.")
self.network.set_state(self.state)
print("Building text sampler.")
#sys.stdout.flush()
self.sampler = TextSampler(self.network)
def sample(self, sen_len, sen_num):
sequences = self.sampler.generate(sen_len, sen_num)
ret = ""
seqnum = 0
for sequence in sequences:
try:
eos_pos = sequence.index('</s>')
sequence = sequence[:eos_pos+1]
except ValueError:
pass
except TypeError:
pass
if (len(sequence) < 4):
continue
ret = ret + ' '.join(sequence)
if (seqnum == 0):
ret = "<div class=\"col-md-4\">\n" + ret
elif (seqnum % 2 == 0):
ret = ret + "\n</div><div class=\"col-md-4\">\n"
seqnum = seqnum + 1
return ret + "\n<div>\n"
vocabulary = Vocabulary.from_state(state)
print("Number of words in vocabulary:", vocabulary.num_words())
print("Number of words in shortlist:", vocabulary.num_shortlist_words())
print("Number of word classes:", vocabulary.num_classes())
print("Building neural network.")
sys.stdout.flush()
architecture = Architecture.from_state(state)
network = Network(architecture, vocabulary, mode=Network.Mode(minibatch=False))
print("Restoring neural network state.")
network.set_state(state)
return network
#model = tlm.Network.from_file('kalevalaV100.h5')
model = restoreModel(modelPath)
sampler = TextSampler(model)
#samp = sampler.generate(15, num_sequences=30)
def printSample(samp):
allwords = ''
for sequence in samp:
pstr = ''
for i,s in enumerate(sequence):
if i > 0:
pstr = pstr + s + ' '
#print(pstr)
allwords += sequence[-1] + ' '
return allwords
