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")
# https://github.com/mfshiu/nlp_ner.git
# coding: utf-8
import sys
sys.path.append('..')
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from attention_seq2seq import AttentionSeq2seq
# 載入資料
(x_train, t_train), (x_test, t_test) = sequence.load_data('train_33839.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 反轉輸入內容
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# 設定超參數
vocab_size = len(char_to_id)
wordvec_size = int(16 / 1)
hidden_size = int(256 * 2)
batch_size = int(128 * 2)
max_epoch = int(len(x_train) / 2000)
max_grad = 5.0
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
# coding: utf-8
import sys
sys.path.append('..')
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from seq2seq import Seq2seq
from peeky_seq2seq import PeekySeq2seq
# 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()
# Reverse input? =================================================
is_reverse = False # 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
hideen_size = 128
batch_size = 128
max_epoch = 25
max_grad = 5.0
# Normal or Peeky? ==============================================
# coding: utf-8
import sys
sys.path.append('..')
from dataset import sequence
(x_train, t_train), (x_test, t_test) = \
sequence.load_data('addition.txt', seed=1984)
char_to_id, id_to_char = sequence.get_vocab()
print(x_train.shape, t_train.shape)
print(x_test.shape, t_test.shape)
# (45000, 7) (45000, 5)
# (5000, 7) (5000, 5)
print(x_train[0])
print(t_train[0])
# [ 3 0 2 0 0 11 5]
# [ 6 0 11 7 5]
print(''.join([id_to_char[c] for c in x_train[0]]))
print(''.join([id_to_char[c] for c in t_train[0]]))
# 71+118
# _189
# coding: utf-8
import sys
import os
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from attention_seq2seq import AttentionSeq2seq
from ch07.seq2seq import Seq2seq
from ch07.peeky_seq2seq import PeekySeq2seq
# データの読み込み
(x_train, t_train), (x_val, t_val) = sequence.load_data('date.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 入力文を反転
x_train, x_val = x_train[:, ::-1], x_val[:, ::-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)
# model = Seq2seq(vocab_size, wordvec_size, hidden_size)
import sys, os
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
from dataset import sequence
(x_train, t_train), (x_test,
t_test) = sequence.load_data('../dataset/addition.txt',
seed=1984)
char_to_id, id_to_char = sequence.get_vocab()
print(x_train.shape, t_train.shape)
print(x_test.shape, t_test.shape)
print(x_train[0])
print(t_train[0])
print(''.join([id_to_char[c] for c in x_train[0]]))
print(''.join([id_to_char[c] for c in t_train[0]]))
# coding: utf-8
import sys, os
sys.path.append(os.pardir)
from dataset import sequence
(x_train, t_train), (x_val, t_val) = \
sequence.load_data("addition.txt")
char_to_id, id_to_char = sequence.get_vocab()
print(x_train.shape, t_train.shape)
print(x_val.shape, t_val.shape)
# (45000, 7) (45000, 5)
# (5000, 7) (5000, 5)
print(x_train[0])
print(t_train[0])
# [ 3 0 2 0 0 11 5]
# [ 6 0 11 7 5]
# coding: utf-8
import sys
import os
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from seq2seq import Seq2seq
from peeky_seq2seq import PeekySeq2seq
# データセットの読み込み
(x_train, t_train), (x_val, t_val) = sequence.load_data('addition.txt')
char_to_id, id_to_char = sequence.get_vocab()
# Reverse input? =================================================
is_reverse = False # True
if is_reverse:
x_train, x_val = x_train[:, ::-1], x_val[:, ::-1]
# ================================================================
# ハイパーパラメータの設定
vocab_size = len(char_to_id)
wordvec_size = 16
hideen_size = 128
batch_size = 128
max_epoch = 25
max_grad = 5.0
# coding: utf-8
import sys
sys.path.append('..')
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from attention_seq2seq import AttentionSeq2seq
# 載入資料
(x_train, t_train), (x_test, t_test) = sequence.load_data('ner_valid.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 反轉輸入內容
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# 設定超參數
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)
# model = Seq2seq(vocab_size, wordvec_size, hidden_size)
# model = PeekySeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
# coding: utf-8
import sys
sys.path.append('..')
from dataset import sequence
(x_train, t_train), (x_test, t_test) = \
sequence.load_data("addition.txt", seed=1984)
char_to_id, id_to_char = sequence.get_vocab()
print(x_train.shape, t_train.shape)
print(x_test.shape, t_test.shape)
# (45000, 7) (45000, 5)
# (5000, 7) (5000, 5)
print(x_train[0])
print(t_train[0])
# [ 3 0 2 0 0 11 5]
# [ 6 0 11 7 5]
# https://github.com/mfshiu/nlp_ner.git
# coding: utf-8
import sys
sys.path.append('..')
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from attention_seq2seq import AttentionSeq2seq
# 載入資料
(x_train, t_train), (x_test, t_test) = sequence.load_data('train3_70000.txt')
char_to_id, id_to_char = sequence.get_vocab()
# 反轉輸入內容
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
# 設定超參數
vocab_size = len(char_to_id)
wordvec_size = int(16/1)
hidden_size = int(256*2)
batch_size = int(128*2)
max_epoch = max(10, int(len(x_train) / 15000))
max_grad = 5.0
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
optimizer = Adam()
trainer = Trainer(model, optimizer)
# coding: utf-8
import sys
sys.path.append('..')
import numpy as np
from dataset import sequence
import matplotlib.pyplot as plt
from ch08.attention_seq2seq import AttentionSeq2seq
(x_train, t_train), (x_test, t_test) = \
sequence.load_data('date.txt')
char_to_id, id_to_char = sequence.get_vocab()
# Reverse input
x_train, x_test = x_train[:, ::-1], x_test[:, ::-1]
vocab_size = len(char_to_id)
wordvec_size = 16
hidden_size = 256
model = AttentionSeq2seq(vocab_size, wordvec_size, hidden_size)
model.load_params()
_idx = 0
def visualize(attention_map, row_labels, column_labels):
fig, ax = plt.subplots()
ax.pcolor(attention_map, cmap=plt.cm.Greys_r, vmin=0.0, vmax=1.0)
ax.patch.set_facecolor('black')
return sampled
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)
import sys
sys.path.append('..')
import numpy as np
import matplotlib.pyplot as plt
from dataset import sequence
from common.optimizer import Adam
from common.trainer import Trainer
from common.util import eval_seq2seq
from ch07.seq2seq import Seq2seq
(x_train, t_train), (x_test, t_test) = sequence.load_data('../dataset/minus.txt')
char_to_id, id_to_char = sequence.get_vocab()
vocab_size = len(char_to_id)
wordvec_size = 16
hideen_size = 128
batch_size = 128
max_epoch = 25
max_grad = 5.0
model = Seq2seq(vocab_size, wordvec_size, hideen_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)