def main():
# ハイパーパラメータの設定
window_size = 5
hidden_size = 100
batch_size = 100
max_epoch = 10
# データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
# モデルなどの生成
model = CBOW(vocab_size, hidden_size, window_size, corpus)
optimizer = Adam()
trainer = Trainer(model, optimizer)
# 学習開始
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot()
# 後ほど利用できるように、必要なデータを保存
word_vecs = model.word_vecs
params = {}
params['word_vecs'] = word_vecs.astype(np.float16)
params['word_to_id'] = word_to_id
params['id_to_word'] = id_to_word
pkl_file = 'cbow_params.pkl'
with open(pkl_file, 'wb') as f:
pickle.dump(params, f, -1)
def main():
max_epoch = 300
batch_size = 30
hidden_size = 10
output_size = 3
learning_rate = 1.0
x, t = spiral.load_data()
model = TwoLayerNet(2, hidden_size, output_size)
optimizer = SGD(learning_rate)
trainer = Trainer(model, optimizer)
trainer.fit(x, t, max_epoch, batch_size)
trainer.plot()
def main():
window_size = 1
hidden_size = 5
batch_size = 3
max_epoch = 1000
text = 'You say goodbye and I say hello.'
corpus, word_to_id, id_to_word = preprocess(text)
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
target = convert_one_hot(target, vocab_size)
contexts = convert_one_hot(contexts, vocab_size)
model = SimpleCBOW(vocab_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot()
def test_train_word2vec_model():
"""word2vecモデルの学習
"""
window_size = 1
hidden_size = 5 # 単語の分散表現ベクトルの次元数
batch_size = 3
max_epoch = 1000
text = 'You say goodbye and I say hello.'
# コーパスの作成
corpus, word_to_id, id_to_word = preprocess(text)
# コンテキストとターゲットの作成
vocab_size = len(word_to_id)
contexts, target = create_context_target(corpus, window_size)
target = convert_one_hot(target, vocab_size)
contexts = convert_one_hot(contexts, vocab_size)
print("one-hot target: ", target)
print("one-hot contexts: ", contexts)
# CBOWモデル
model = SimpleCBOW(vocab_size, hidden_size)
optimizer = Adam()
# trainer
trainer = Trainer(model, optimizer)
# 学習
trainer.fit(contexts, target, max_epoch=max_epoch, batch_size=batch_size)
trainer.plot()
# CBOWの重み(W_in)を取得する
word_vecs = model.word_vecs
for word_id, word in id_to_word.items():
print(word, word_vecs[word_id])
max_epoch = 1000
text = 'You say goodbye and I say hello.'
corpus, word_to_id, id_to_word = preprocess(text)
vocab_size = len(word_to_id)
contexts, target = create_contexts_target, convert_one_hot
window_size = 1
hidden_size = 5
batch_size = 3
max_epoch = 1000
text = 'You say goodbye and I say hello.'
corpus, word_to_id, id_to_word = preprocess(text)
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
target = convert_one_hot(target, vocab_size)
contexts = convert_one_hot(contexts, vocab_size)
model = SimpleCBOW(vocab_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot()
word_vecs = model.word_vecs
for word_id, word in id_to_word.items():
print(word, word_vecs[word_id])
x_test,
t_test,
guess_test,
encoding=encoding)
# Save result as csv as utf-8 with BOM
# Excelで文字化けさせたくない場合はこっちで保存
result_train_csv = save_dir / ("result_" + dataset_name + "_" + modelname +
"_train_bom.csv")
result_test_csv = save_dir / ("result_" + dataset_name + "_" + modelname +
"_test_bom.csv")
df_result_train = seq.result_to_csv(result_train_csv,
x_train,
t_train,
guess_train,
encoding="utf_8_sig")
df_result_test = seq.result_to_csv(result_test_csv,
x_test,
t_test,
guess_test,
encoding="utf_8_sig")
# Plot learning curve and save it as png image
image_path = save_dir / ('result_' + dataset_name + "_" + modelname + '.png')
trainer.plot(image_path=image_path, log_scale=False)
# Save parameters
pickle_path = model_dir / (dataset_name + "_" + modelname + '_epoch' +
max_epoch + "_" + timestamp + '.pkl')
model.save_params(file_name=pickle_path)
import sys
sys.path.append("..")
from common.trainer import Trainer
from common.optimizer import Adam
from simple_cbow import SimpleCBOW
from common.util import preprocess, create_contexts_target, convert_one_hot
window_size = 1
hidden_size = 5
batch_size = 3
max_epoch = 1000
text = 'You say goodbye and I say hello .'
corpus, word_to_id, id_to_word = preprocess(text)
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
target = convert_one_hot(target, vocab_size)
contexts = convert_one_hot(contexts, vocab_size)
model = SimpleCBOW(vocab_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot(path='../output/03-train.png')
word_vecs = model.word_vecs
for word_id, word in id_to_word.items():
print(word, word_vecs[word_id])
import sys
sys.path.append("..")
from common.trainer import Trainer
from common.optimizer import Adam
from simple_skip_gram import SimpleSkipGram
from common.util import preprocess, create_contexts_target, convert_one_hot
window_size = 1
hidden_size = 5
batch_size = 3
max_epoch = 1000
text = 'You say goodbye and I say hello .'
corpus, word_to_id, id_to_word = preprocess(text)
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
target = convert_one_hot(target, vocab_size)
contexts = convert_one_hot(contexts, vocab_size)
model = SimpleSkipGram(vocab_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot(path='../output/03-train_skip_gram.png')
word_vecs = model.word_vecs
for word_id, word in id_to_word.items():
print(word, word_vecs[word_id])
# model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
print("Cross Validation: iter", str(i+1))
# Train
trainer.fit(x_train, t_train, x_test, t_test,
max_epoch=max_epoch,
batch_size=batch_size,
max_grad=max_grad)
# Inference
start_id = seq.start_id
sample_size = seq.sample_size
guess_train = model.generate(x_train, start_id, sample_size)
guess_test = model.generate(x_test, start_id, sample_size)
# Save result as csv
suffix = "_cv" + str(i + 1)
result_train_csv = result_dir / ("result_" + dataset_name + "_" + model.__class__.__name__ + "_train"+ suffix +".csv")
result_test_csv = result_dir / ("result_" + dataset_name + "_" + model.__class__.__name__ + "_test"+ suffix +".csv")
seq.result_to_csv(result_train_csv, x_train, t_train, guess_train, encoding=encoding)
seq.result_to_csv(result_test_csv, x_test, t_test, guess_test, encoding=encoding)
# Plot learning curve and save it as png image
image_path = result_dir / ('result_' + dataset_name + "_" + model.__class__.__name__ + suffix + '.png')
trainer.plot(image_path)
# release memory
del model, optimizer, trainer
# coding: utf-8
import sys
sys.path.append('..') # 親ディレクトリのファイルをインポートするための設定
from common.optimizer import SGD
from common.trainer import Trainer
from dataset import spiral
from two_layer_net import TwoLayerNet
# ハイパーパラメータの設定
max_epoch = 300
batch_size = 30
hidden_size = 10
learning_rate = 1.0
x, t = spiral.load_data()
model = TwoLayerNet(input_size=2, hidden_size=hidden_size, output_size=3)
optimizer = SGD(lr=learning_rate)
trainer = Trainer(model, optimizer)
trainer.fit(x, t, max_epoch, batch_size, eval_interval=10)
trainer.plot(path='../output/01-plot.png')
