Skip to content

[ch04]各epochごとにすべての訓練データを見るようにする #90

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[ch04]各epochごとにすべての訓練データを見るようにする #90

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 29 additions & 26 deletions ch04/train_neuralnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

iters_num = 10000 # 繰り返しの回数を適宜設定する
epoch_num = 20
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1
Expand All @@ -20,30 +20,33 @@
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)

for i in range(iters_num):
batch_mask = np.random.choice(train_size, batch_size)
x_batch = x_train[batch_mask]
t_batch = t_train[batch_mask]

# 勾配の計算
#grad = network.numerical_gradient(x_batch, t_batch)
grad = network.gradient(x_batch, t_batch)

# パラメータの更新
for key in ('W1', 'b1', 'W2', 'b2'):
network.params[key] -= learning_rate * grad[key]

loss = network.loss(x_batch, t_batch)
train_loss_list.append(loss)

if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, t_train)
test_acc = network.accuracy(x_test, t_test)
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print("train acc, test acc | " + str(train_acc) + ", " + str(test_acc))
iter_per_epoch = max(train_size // batch_size, 1)


for epoch in range(epoch_num):
perm = np.random.permutation(train_size)

for i in range(iter_per_epoch):
batch_mask = perm[i * batch_size : (i + 1) * batch_size]
x_batch = x_train[batch_mask]
t_batch = t_train[batch_mask]

# 勾配の計算
#grad = network.numerical_gradient(x_batch, t_batch)
grad = network.gradient(x_batch, t_batch)

# パラメータの更新
for key in ('W1', 'b1', 'W2', 'b2'):
network.params[key] -= learning_rate * grad[key]

loss = network.loss(x_batch, t_batch)
train_loss_list.append(loss)

train_acc = network.accuracy(x_train, t_train)
test_acc = network.accuracy(x_test, t_test)
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print("train acc, test acc | " + str(train_acc) + ", " + str(test_acc))

# グラフの描画
markers = {'train': 'o', 'test': 's'}
Expand All @@ -54,4 +57,4 @@
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()
plt.show()