def __train(lr, weight_decay, epocs=50):
network = MultiLayerNet(input_size=784,
hidden_size_list=[100, 100, 100, 100, 100, 100],
output_size=10,
weight_decay_lambda=weight_decay)
trainer = Trainer(network,
x_train,
t_train,
x_val,
t_val,
epochs=epocs,
mini_batch_size=100,
optimizer='sgd',
optimizer_param={'lr': lr},
verbose=False)
trainer.train()
return trainer.test_acc_list, trainer.train_acc_list
# ================================================================
# 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
# Normal or Peeky? ==============================================
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, is_reverse)
network = SimpleConvNet(input_dim=(1, 28, 28),
conv_param={
'filter_num': 30,
'filter_size': 5,
'pad': 0,
'stride': 1
},
hidden_size=100,
output_size=10,
weight_init_std=0.01)
trainer = Trainer(network,
x_train,
t_train,
x_test,
t_test,
epochs=max_epochs,
mini_batch_size=100,
optimizer='Adam',
optimizer_param={'lr': 0.001},
evaluate_sample_num_per_epoch=1000)
trainer.train()
# パラメータの保存
network.save_params("params.pkl")
print("Saved Network Parameters!")
# グラフの描画
markers = {'train': 'o', 'test': 's'}
x = np.arange(max_epochs)
plt.plot(x, trainer.train_acc_list, marker='o', label='train', markevery=2)
plt.plot(x, trainer.test_acc_list, marker='s', label='test', markevery=2)
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
t_train = t_train[:300]
# Dropuoutの有無、割り合いの設定 ========================
use_dropout = True # Dropoutなしのときの場合はFalseに
dropout_ratio = 0.2
# ====================================================
network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100],
output_size=10, use_dropout=use_dropout, dropout_ration=dropout_ratio)
trainer = Trainer(network, x_train, t_train, x_test, t_test,
epochs=301, mini_batch_size=100,
optimizer='sgd', optimizer_param={'lr': 0.01}, verbose=True)
trainer.train()
train_acc_list, test_acc_list = trainer.train_acc_list, trainer.test_acc_list
# グラフの描画==========
markers = {'train': 'o', 'test': 's'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, marker='o', label='train', markevery=10)
plt.plot(x, test_acc_list, marker='s', label='test', markevery=10)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()
batch_size = 100
max_epoch = 10
# データの読み込み
corpus, word_to_id, id_to_word = ptb.load_data('train')
vocab_size = len(word_to_id)
contexts, target = create_contexts_target(corpus, window_size)
if config.GPU:
contexts, target = to_gpu(contexts), to_gpu(target)
# モデルなどの生成
model = CBOW(vocab_size, hidden_size, window_size, corpus)
# model = SkipGram(vocab_size, hidden_size, window_size, corpus)
optimizer = Adam()
trainer = Trainer(model, optimizer)
# 学習開始
trainer.fit(contexts, target, max_epoch, batch_size)
trainer.plot()
# 後ほど利用できるように、必要なデータを保存
word_vecs = model.word_vecs
if config.GPU:
word_vecs = to_cpu(word_vecs)
params = {}
params['word_vecs'] = word_vecs.astype(np.float16)
params['word_to_id'] = word_to_id
params['id_to_word'] = id_to_word
pkl_file = 'cbow_params.pkl' # or 'skipgram_params.pkl'
with open(pkl_file, 'wb') as f:
# coding: utf-8
import sys
sys.path.append('..') # 親ディレクトリのファイルをインポートするための設定
from src.common import SGD
from src.common import Trainer
from dataset import spiral
from two_layer_net import TwoLayerNet
# ハイパーパラメータの設定
max_epoch = 300
batch_size = 30
hidden_size = 10
learning_rate = 1.0
x, t = spiral.load_data()
model = TwoLayerNet(input_size=2, hidden_size=hidden_size, output_size=3)
optimizer = SGD(lr=learning_rate)
trainer = Trainer(model, optimizer)
trainer.fit(x, t, max_epoch, batch_size, eval_interval=10)
trainer.plot()