def load_text_dataset(path, train_size, valid_size, test_size):
file_name = os.path.join('..', 'datasets', path)
old_dir = os.getcwd()
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)
with open(file_name, 'r') as f:
text = f.read()
os.chdir(old_dir)
vocabulary = create_vocabulary(text)
if test_size is not None:
test_text = text[:test_size]
text = text[test_size:]
else:
test_text = None
if valid_size is not None:
valid_text = text[:valid_size]
text = text[valid_size:]
else:
valid_text = None
if train_size is not None:
train_text = text[:train_size]
else:
train_text = text
return vocabulary, train_text, valid_text, test_text
def get_vocab_by_given_path(file_name, text, create=False):
if os.path.isfile(file_name) and not create:
vocabulary = load_vocabulary_with_unk(file_name)
else:
vocabulary = create_vocabulary(text, with_unk=True)
if not os.path.exists(os.path.dirname(file_name)) and len(
os.path.dirname(file_name)) > 0:
os.makedirs(os.path.dirname(file_name))
with open(file_name, 'w') as f:
f.write(''.join(vocabulary))
vocabulary_size = len(vocabulary)
return vocabulary, vocabulary_size
os.chdir(dname)
#
# with open(conf_file, 'r') as f:
# lines = f.read().split('\n')
dataset_path = os.path.join(*(['..'] * ROOT_HEIGHT +
['datasets', 'text8.txt']))
with open(dataset_path, 'r') as f:
text = f.read()
valid_size = 500
valid_text = text[:valid_size]
train_text = text[valid_size:]
vocabulary = create_vocabulary(text)
vocabulary_size = len(vocabulary)
print(vocabulary_size)
tf.set_random_seed(1)
env = Environment(pupil_class=Lstm,
meta_optimizer_class=ResNet4Lstm,
batch_generator_classes=BatchGenerator,
vocabulary=vocabulary)
add_metrics = ['bpc', 'perplexity', 'accuracy']
NUM_EXERCISES = 10
NUM_UNROLLINGS = 4
OPT_INF_NAME = 'COLD'
OPT_INF_RESTORE_PUPIL_PATHS = [(OPT_INF_NAME, None)]
env.build_pupil(batch_size=32,
def create_vocabulary(texts):
text = ''
for t in texts:
text += t
return create_vocabulary(text)
import tensorflow as tf
from learning_to_learn.environment import Environment
from learning_to_learn.pupils.lstm_for_meta import Lstm, LstmFastBatchGenerator as BatchGenerator
from learning_to_learn.useful_functions import create_vocabulary, get_positions_in_vocabulary
with open('datasets/text8.txt', 'r') as f:
text = f.read()
valid_size = 500
valid_text = text[:valid_size]
train_text = text[valid_size:]
vocabulary = create_vocabulary(train_text + valid_text)
vocabulary_size = len(vocabulary)
env = Environment(Lstm, BatchGenerator, vocabulary=vocabulary)
cpiv = get_positions_in_vocabulary(vocabulary)
add_feed = [
{
'placeholder': 'dropout',
'value': 0.9
} #,
# {'placeholder': 'sampling_prob',
# 'value': {'type': 'linear', 'start': 0., 'end': 1., 'interval': 3000}},
# {'placeholder': 'loss_comp_prob',
# 'value': {'type': 'linear', 'start': 1., 'end': 0., 'interval': 3000}}
]
valid_add_feed = [ # {'placeholder': 'sampling_prob', 'value': 1.},
