How to use cross validation correctly for a deep learning model? How to use cross validation correctly for a deep learning model? How to use cross validation correctly for a deep learning model?
X_train, X_test, y_train, y_test =train_test_split(train, Y, test_size=0.2, random_state=42)
model.compile(loss='BinaryCrossentropy', metrics=['accuracy'], optimizer=optimizer)
kfold = KFold(n_splits=10, shuffle=True)
for train_idx, val_idx in kfold.split(train_x, train_y):
x_train_fold = train_x[train_idx]
y_train_fold = train_y[train_idx]
x_val_fold = train_x[val_idx]
y_val_fold = train_y[val_idx]
history1 = model.fit(train_x, train_y,validation_data=(x_val_fold, y_val_fold) , batch_size=32, epochs=int(number_epoch), shuffle=False)
# evaluate the model on the test set
test_loss, test_acc = model.evaluate(test_x, test_y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
