window_size = 5
hidden_size = 100
batch_size = 100
max_epoch = 10
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=window_size)
# モデル
#model = CBOW(vocab_size, hidden_size, window_size, corpus)
model = SkipGram(vocab_size, hidden_size, window_size, corpus)
optimizer = Adam()
# 学習
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch=max_epoch, batch_size=batch_size)
# plot
trainer.plot('chap4_ptb.png')
# 単語の分散表現保存
params = {}
params['word_vecs'] = model.word_vecs.astype(np.float16)
params['word_to_id'] = word_to_id
params['id_to_word'] = id_to_word
#fname = 'cbow_params.pkl'
fname = 'skip_gram_params.pkl'
with open(fname, 'wb') as f:
pickle.dump(params, f, -1)
if __name__ == '__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=window_size)
contexts = convert_one_hot(contexts, vocab_size=vocab_size)
target = convert_one_hot(target, vocab_size=vocab_size)
# モデル
#model = SimpleCBOW(vocab_size, hidden_size)
model = SimpleSkipGram(vocab_size, hidden_size)
optimizer = Adam()
#optimizer = SGD()
# 学習
trainer = Trainer(model, optimizer)
trainer.fit(contexts, target, max_epoch=max_epoch, batch_size=batch_size)
# plot
trainer.plot('chap3.png')
# 単語の分散表現print
for word, word_id in word_to_id.items():
print('{0} {1}'.format(word, model.word_vecs[word_id]))
# coding: utf-8
import sys
from trainers import Trainer
from two_layers_net import TwoLayersNet
from optimizers import SGD
from dataset import spiral
if __name__ == '__main__':
max_epoch = 300
batch_size = 30
hidden_size = 10
learning_rate = 1.0
# データ, モデル, optimizer
x, t = spiral.load_data()
model = TwoLayersNet(input_size=2, hidden_size=hidden_size, output_size=3)
opt = SGD(learning_rate)
# 学習
trainer = Trainer(model, opt)
trainer.fit(x, t, max_epoch, batch_size, eval_interval=10)
# plot
trainer.plot('chap1.png')
