def main() -> None:
(x_train, t_train), (x_test, t_test) = sequence.load_data('addition.txt')
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
char_to_id, id_to_char = sequence.get_vocab()
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 128
batch_size = 128
max_epoch = 25
max_grad = 5.0
model = PeekySeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
acc_list = []
for epoch in range(1, max_epoch+1):
trainer.fit(x_train, t_train, max_epoch=1, batch_size=batch_size, max_grad=max_grad)
correct_num = 0
for i in range(len(x_test)):
question, correct = x_test[[i]], t_test[[i]]
verbose = i < 10
correct_num += eval_seq2seq(model, question, correct, id_to_char, verbose)
acc = float(correct_num) / len(x_test)
acc_list.append(acc)
print(f'val acc {acc*100}%')
print('DONE')
def main():
(x_train, t_train), (x_test, t_test) = load_data('addition.txt', seed=1984)
char_to_id, id_to_char = get_vocab()
print(x_train.shape, t_train.shape)
print(x_test.shape, t_test.shape)
print(''.join([id_to_char[c] for c in x_train[0]]))
print(''.join([id_to_char[c] for c in t_train[0]]))
def main():
# データセットの読み込み
(x_train, t_train), (x_test, t_test) = sequence.load_data('addition.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 入力列を逆順にするとSeq2Se2の精度が上がるらしいが。。。クソ理論
is_reverse = True
if is_reverse:
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# ハイパーパラメータの設定
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 128
batch_size = 128
max_epoch = 25
max_grad = 5.0
# モデル/オプティマイザ/トレーナーの生成
# model = Seq2seq(vocab_size, wordvec_size, hidden_size)
model = PeekySeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
acc_list = []
for epoch in range(max_epoch):
trainer.fit(x_train,
t_train,
max_epoch=1,
batch_size=batch_size,
max_grad=max_grad)
correct_num = 0
for i in range(len(x_test)):
question, correct = x_test[[i]], t_test[[i]]
verbose = i < 10
correct_num += eval_seq2seq(model, question, correct, id_to_char,
verbose)
acc = float(correct_num) / len(x_test)
acc_list.append(acc)
print(f'val acc {acc * 100}')
def main():
# データの読み込み
(x_train, t_train), (x_test, t_test) = sequence.load_data('date.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 入力文を反転
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# ハイパーパラメータの設定
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 256
batch_size = 128
max_epoch = 10
max_grad = 5.0
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
acc_list = []
for epoch in range(max_epoch):
trainer.fit(x_train,
t_train,
max_epoch=1,
batch_size=batch_size,
max_grad=max_grad)
correct_num = 0
for i in range(len(x_test)):
question, correct = x_test[[i]], t_test[[i]]
verbose = i < 10
correct_num += eval_seq2seq(model,
question,
correct,
id_to_char,
verbose,
is_reverse=True)
acc = float(correct_num) / len(x_test)
acc_list.append(acc)
print('val acc %.3f%%' % (acc * 100))
def main() -> None:
(x_train, t_train), (x_test, t_test) = sequence.load_data('data.txt')
char_to_id, id_to_char = sequence.get_vocab()
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 256
batch_size = 128
max_epoch = 10
max_grad = 5.0
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
acc_list = []
for epoch in range(max_epoch):
trainer.fit(x_train,
t_train,
max_epoch=1,
batch_size=batch_size,
max_grad=max_grad)
correct_num = 0
for i in range(len(x_test)):
question, correct = x_test[[i]], t_test[[i]]
verbose = i < 10
correct_num += eval_seq2seq(model,
question,
correct,
id_to_char,
verbose,
is_reverse=True)
acc = float(correct_num) / len(x_test)
acc_list.append(acc)
print(f"val acc {acc*100}%")
model.save_params()
print("DONE")
class AttentionSeq2seq(Seq2seq):
def __init__(self, vocab_size, wordvec_size, hidden_size):
args = vocab_size, wordvec_size, hidden_size
self.encoder = AttentionEncoder(*args)
self.decoder = AttentionDecoder(*args)
self.softmax = TimeSoftmaxWithLoss()
self.params = self.encoder.params + self.decoder.params
self.grads = self.encoder.grads + self.decoder.grads
if __name__ == "__main__":
(x_train, t_train), (x_test, t_test) = sequence.load_data('date.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 入力文を反転
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# ハイパーパラメータの設定
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 256
batch_size = 128
max_epoch = 4
max_grad = 5.0
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()