def main():
batch_size = 20
wordvec_size = 650
hidden_size = 650
time_size = 35
lr = 20.0
#max_epoch = 40
max_epoch = 1
max_grad = 0.25
dropout = 0.5
corpus, word_to_id, _ = ptb.load_data('train')
corpus_val, _, _ = ptb.load_data('val')
corpus_test, _, _ = ptb.load_data('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 _ in range(max_epoch):
trainer.fit(xs,
ts,
1,
batch_size,
time_size,
max_grad,
eval_interval=20)
model.reset_state()
ppl = eval_perplexity(model, corpus_val)
print(f'valid perplexity: {ppl}')
if best_ppl > ppl:
best_ppl = ppl
model.save_params()
else:
lr /= 4.0
optimizer.lr = lr
model.reset_state()
print('-' * 50)
model.reset_state()
ppl_test = eval_perplexity(model, corpus_test)
print(f'valid perplexity: {ppl_test}')
print('DONE')
def main():
# ハイパーパラメータの設定
batch_size = 20
wordvec_size = 650
hidden_size = 650
time_size = 35
lr = 20.0
max_epoch = 40
max_grad = 0.25
dropout = 0.5
# 学習データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_val, _, _ = ptb.load_data('val')
corpus_test, _, _ = ptb.load_data('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
optimizer.lr = lr
model.reset_state()
print('-' * 50)
hidden_size = 650
time_size = 35
lr = 20.0
max_epoch = 40
max_grad = 0.25
dropout = 0.5
# 学習データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
corpus_val, _, _ = ptb.load_data('val')
corpus_test, _, _ = ptb.load_data('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)
# coding: utf-8
import sys
sys.path.append('..')
from rnnlm import Rnnlm
from better_rnnlm import BetterRnnlm
from dataset import ptb
from common.util import eval_perplexity
if __name__ == '__main__':
# model = Rnnlm()
model = BetterRnnlm()
model.load_params()
corpus, _, _ = ptb.load_data('test')
model.reset_state()
ppl_test = eval_perplexity(model, corpus)
print('test perplexity: ', ppl_test)