質問編集履歴
2
誤字の修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
Kerasのmodel.fitにvalidation_dataを入れると学習が異常に遅くなります．
|
|
2
2
|
|
|
3
3
|
model=Sequential()
|
|
4
|
-
model.add(Dense(14, activation="tanh", input_dim=
|
|
4
|
+
model.add(Dense(14, activation="tanh", input_dim=6, kernel_regularizer = regularizers.l2(0.03)))
|
|
5
5
|
model.add(Dense(1, activation="linear", input_dim=14))
|
|
6
6
|
model.compile(loss="mean_squared_error", optimizer=tf.optimizers.Adam(learning_rate=0.02), metrics=[tf.keras.metrics.RootMeanSquaredError()])
|
|
7
7
|
num_epoch=300
|
1
誤字の修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
batch_size=8
|
|
10
10
|
history = model.fit(X_train_std, Y_train_std, epochs=num_epoch, batch_size=batch_size, validation_data=(X_val_std, Y_val_std))
|
|
11
|
-
これで実行すると約2分ほど学習に時間がかかります．(X_train_stdは(24,6)で，X_
|
|
11
|
+
これで実行すると約2分ほど学習に時間がかかります．(X_train_stdは(24,6)で，X_val_stdは(5,6)の配列です)
|
|
12
12
|
|
|
13
13
|
model.fitの部分でvalidation_data=(X_val_std, Y_val_std)を除いた
|
|
14
14
|
history = model.fit(X_train_std, Y_train_std, epochs=num_epoch, batch_size=batch_size)
|