from common.optimizer import SGD
from common.trainer import RnnlmTrainer
from dataset import ptb
from ch05.simple_rnnlm import SimpleRnnlm
# 하이퍼파라미터 설정
batch_size = 10
wordvec_size = 100
hidden_size = 100 # RNN의 은닉 상태 벡터의 원소 수
time_size = 5 # RNN을 펼치는 크기
lr = 0.1
max_epoch = 100
# 학습 데이터 읽기
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_size = 1000 # 테스트 데이터셋을 작게 설정
corpus = corpus[:corpus_size]
vocab_size = int(max(corpus) + 1)
xs = corpus[:-1] # 입력
ts = corpus[1:] # 출력（정답 레이블）
# 모델 생성
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_val, _, _ = ptb.load_data('val')
corpus_test, _, _ = ptb.load_data('test')
if config.GPU:
corpus = to_gpu(corpus)
corpus_val = to_gpu(corpus_val)
corpus_test = to_gpu(corpus_test)
vocab_size = len(word_to_id)
xs = corpus[:-1]
ts = corpus[1:]
model = BetterRnnlm(vocab_size, wordvec_size, hidden_size, dropout)
optimizer = SGD(lr)
trainer = RnnlmTrainer(model, optimizer)
best_ppl = float('inf')
for epoch in range(max_epoch):
trainer.fit(xs, ts, max_epoch=1, batch_size=batch_size,
time_size=time_size, max_grad=max_grad)
model.reset_state()
ppl = eval_perplexity(model, corpus_val)
print('valid perplexity: ', ppl)
if best_ppl > ppl:
best_ppl = ppl
model.save_params()
else:
lr /= 4.0
time_size = 35 # RNNを展開するサイズ
lr = 20.0
max_epoch = 4
max_grad = 0.25
# 学習データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_test, _, _ = ptb.load_data('test')
vocab_size = len(word_to_id)
xs = corpus[:-1]
ts = corpus[1:]
# モデルの生成
model = Rnnln(vocab_size, wordvec_size, hidden_size)
optimizer = SGD(lr)
trainer = RnnlmTrainer(model, optimizer)
# 勾配クリッピングを適用して学習
trainer.fit(xs, ts, max_epoch, batch_size, time_size, max_grad, eval_interval=20)
trainer.plot(ylim=(0, 500))
# テストデータで評価
model.reset_state()
ppl_test = eval_perplexity(model, corpus_test)
print('test perplexity: ', ppl_test)
# パラメーターの保存
model.save_params()
# 結果
# test perplexity: 134.61532778421517
import sys
sys.path.append('..')
from common.optimizer import SGD
from common.trainer import RnnlmTrainer
from dataset import ptb
from 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(path='../output/05-train.png')
sys.path.append('..')
from common.optimizer import SGD
from common.trainer import RnnlmTrainer # RnnlmTrainer 는 RNNLM 의 학습을 클래스 안으로 숨겨준다.
from dataset import ptb
from simple_rnnlm import SimpleRnnlm
# 하이퍼파라미터 설정
batch_size = 10
wordvec_size = 100
hidden_size = 100 # RNN의 은닉 상태 벡터의 원소 수
time_size = 5 # RNN을 펼치는 크기
lr = 0.1
max_epoch = 100
# 학습 데이터 읽기
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_size = 1000 # 테스트 데이터셋을 작게 설정
corpus = corpus[:corpus_size]
vocab_size = int(max(corpus) + 1)
xs = corpus[:-1] # 입력
ts = corpus[1:] # 출력（정답 레이블）
# 모델 생성
model = SimpleRnnlm(vocab_size, wordvec_size, hidden_size)
optimizer = SGD(lr)
trainer = RnnlmTrainer(model, optimizer) # 먼저 model, optimzer 을 주어 초기화
trainer.fit(xs, ts, max_epoch, batch_size, time_size) # fit 메서드를 통해 학습을 수행한다.
trainer.plot()
from dataset import ptb
from rnnlm import Rnnlm
batch_size = 20
wordvec_size = 100
hidden_size = 100
time_size = 35
lr = 20.0
max_epoch = 4
max_grad = 0.25
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_test, _, _ = ptb.load_data('test')
vocab_size = len(word_to_id)
xs = corpus[:-1]
ts = corpus[1:]
model = Rnnlm(vocab_size, wordvec_size, hidden_size)
optimizer = SGD(lr)
trainer = RnnlmTrainer(model, optimizer)
trainer.fit(xs, ts, max_epoch, batch_size, time_size, max_grad, eval_interval=20)
trainer.plot(ylim=(0, 500), path='../output/06-train.png')
model.reset_state()
ppl_test = eval_perplexity(model, corpus_test)
print('Test perplexity: ', ppl_test)
model.save_params()
