sys.path.append('..')
from common.optimizer import SGD
from common.trainer import RnnlmTrainer
from dataset import ptb
from ch05.simple_rnnlm import SimpleRnnlm
# ハイパーパラメータの設定
batch_size = 10
wordvec_size = 100
hidden_size = 100 # RNNの隠れ状態ベクトルの要素数
time_size = 5 # RNNを展開するサイズ
lr = 0.1
max_epoch = 100
# 学習データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_size = 1000 # テスト用にデータセットを小さくする
corpus = corpus[:corpus_size]
vocab_size = int(max(corpus) + 1)
xs = corpus[:-1] # 入力
ts = corpus[1:] # 出力（教師ラベル）
# モデルの生成
model = SimpleRnnlm(vocab_size, wordvec_size, hidden_size)
optimizer = SGD(lr)
trainer = RnnlmTrainer(model, optimizer)
trainer.fit(xs, ts, max_epoch, batch_size, time_size)
trainer.plot()
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_size = 1000
corpus = corpus[:corpus_size]
vocab_size = int(max(corpus) + 1)
xs = corpus[:-1]
ts = corpus[1:]
data_size = len(xs)
print('corpus size: %d, vocabulary size: %d' % (corpus_size, vocab_size))
max_iters = data_size // (batch_size * time_size)
time_idx = 0
total_loss = 0
loss_count = 0
ppl_list = []
model = SimpleRnnlm(vocab_size, wordvec_size, hidden_size)
optimizer = SGD(lr)
jump = (corpus_size - 1) // batch_size
offsets = [i * jump for i in range(batch_size)]
for epoch in range(max_epoch):
for iter in range(max_iters):
batch_x = np.empty((batch_size, time_size), dtype='i')
batch_t = np.empty((batch_size, time_size), dtype='i')
for t in range(time_size):
for i, offset in enumerate(offsets):
batch_x[i, t] = xs[(offset + time_idx) % data_size]
batch_t[i, t] = ts[(offset + time_idx) % data_size]
time_idx += 1