vocab_size = 20000
sentence_length = 100
embedding_dim = 128
hidden_size = 128
reset_cells = True
# setup backend
be = gen_backend(backend=args.backend,
batch_size=batch_size,
rng_seed=args.rng_seed,
device_id=args.device_id,
default_dtype=args.datatype)
# make dataset
path = load_text('imdb', path=args.data_dir)
(X_train, y_train), (X_test, y_test), nclass = Text.pad_data(
path, vocab_size=vocab_size, sentence_length=sentence_length)
print "Vocab size - ", vocab_size
print "Sentence Length - ", sentence_length
print "# of train sentences", X_train.shape[0]
print "# of test sentence", X_test.shape[0]
train_set = DataIterator(X_train, y_train, nclass=2)
valid_set = DataIterator(X_test, y_test, nclass=2)
# weight initialization
init_emb = Uniform(low=-0.1/embedding_dim, high=0.1/embedding_dim)
init_glorot = GlorotUniform()
layers = [
LookupTable(vocab_size=vocab_size, embedding_dim=embedding_dim, init=init_emb),
vocab_size = 20000
sentence_length = 100
embedding_dim = 128
hidden_size = 128
reset_cells = True
# setup backend
be = gen_backend(backend=args.backend,
batch_size=batch_size,
rng_seed=args.rng_seed,
device_id=args.device_id,
default_dtype=args.datatype)
# make dataset
path = load_text('imdb', path=args.data_dir)
(X_train, y_train), (X_test, y_test), nclass = Text.pad_data(
path, vocab_size=vocab_size, sentence_length=sentence_length)
print "Vocab size - ", vocab_size
print "Sentence Length - ", sentence_length
print "# of train sentences", X_train.shape[0]
print "# of test sentence", X_test.shape[0]
import numpy as np
train_set = DataIterator(X_train, y_train, nclass=2)
test_set = DataIterator(X_test, y_test, nclass=2)
# weight initialization
init_emb = Uniform(low=-0.1/embedding_dim, high=0.1/embedding_dim)
init_glorot = GlorotUniform()
layers = [
print(
'batch_size: %s \nvocab_size: %s \nsentence_length: %s \nembedding_dim: %s \nhidden_size: %s'
% (batch_size, vocab_size, sentence_length, embedding_dim, hidden_size))
# setup backend
be = gen_backend(backend=args.backend,
batch_size=batch_size,
rng_seed=args.rng_seed,
device_id=args.device_id,
default_dtype=args.datatype)
# make dataset
(X_train, y_train), (X_test, y_test), nclass = Text.pad_data(
os.path.join(
data_root,
'train_valid_text_index_in_binary_label_shuffled_10000.pickle'),
vocab_size=vocab_size,
sentence_length=sentence_length)
print "Vocab size - ", vocab_size
print "Sentence Length - ", sentence_length
print "# of train sentences", X_train.shape[0]
print "# of test sentence", X_test.shape[0]
train_set = DataIterator(X_train, y_train, nclass=2)
valid_set = DataIterator(X_test, y_test, nclass=2)
# weight initialization
init_emb = Uniform(low=-0.1 / embedding_dim, high=0.1 / embedding_dim)
init_glorot = GlorotUniform()
hidden_size = 128
reset_cells = True
print('batch_size: %s \nvocab_size: %s \nsentence_length: %s \nembedding_dim: %s \nhidden_size: %s' %
(batch_size, vocab_size, sentence_length, embedding_dim, hidden_size))
# setup backend
be = gen_backend(backend=args.backend,
batch_size=batch_size,
rng_seed=args.rng_seed,
device_id=args.device_id,
default_dtype=args.datatype)
# make dataset
(X_train, y_train), (X_test, y_test), nclass = Text.pad_data(
os.path.join(
data_root, 'train_valid_text_index_in_binary_label_shuffled_10000.pickle'),
vocab_size=vocab_size, sentence_length=sentence_length)
print "Vocab size - ", vocab_size
print "Sentence Length - ", sentence_length
print "# of train sentences", X_train.shape[0]
print "# of test sentence", X_test.shape[0]
train_set = DataIterator(X_train, y_train, nclass=2)
valid_set = DataIterator(X_test, y_test, nclass=2)
# weight initialization
init_emb = Uniform(low=-0.1 / embedding_dim, high=0.1 / embedding_dim)
init_glorot = GlorotUniform()
layers = [
