如何在验证/测试阶段关闭 dropout？

Question

我是神经网络的新手。我知道在验证/测试期间必须关闭 dropout，因为 dropout 会使神经元故意输出“错误”值。因此，最好是在准确性方面获得良好的结果。 我怎样才能在我的代码中做到这一点？该数据集由 18 个特征、1 个标签组成，是一个回归问题。

import pandas as pd
import numpy as np

from sklearn.ensemble import RandomForestRegressor
from sklearn.feature_selection import SelectFromModel
from sklearn import preprocessing

from sklearn.model_selection import train_test_split

from matplotlib import pyplot as plt

import keras
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, BatchNormalization
from tensorflow.keras.callbacks import EarlyStopping
from keras import optimizers
from sklearn.metrics import r2_score
from keras import regularizers
from keras import backend
from tensorflow.keras import regularizers
from keras.regularizers import l2

# =============================================================================
# Scelgo il test size
# =============================================================================
test_size = 0.2

dataset = pd.read_csv('DataSet.csv', decimal=',', delimiter = ";")

label = dataset.iloc[:,-1]
features = dataset.drop(columns = ['Label'])

y_max_pre_normalize = max(label)
y_min_pre_normalize = min(label)

def denormalize(y):
    final_value = y*(y_max_pre_normalize-y_min_pre_normalize)+y_min_pre_normalize
    return final_value

# =============================================================================
# Split
# =============================================================================

X_train1, X_test1, y_train1, y_test1 = train_test_split(features, label, test_size = test_size, shuffle = True)

y_test2 = y_test1.to_frame()
y_train2 = y_train1.to_frame()

# =============================================================================
# Normalizzo
# =============================================================================
scaler1 = preprocessing.MinMaxScaler()
scaler2 = preprocessing.MinMaxScaler()
X_train = scaler1.fit_transform(X_train1)
X_test = scaler2.fit_transform(X_test1)


scaler3 = preprocessing.MinMaxScaler()
scaler4 = preprocessing.MinMaxScaler()
y_train = scaler3.fit_transform(y_train2)
y_test = scaler4.fit_transform(y_test2)



# =============================================================================
# Creo la rete
# =============================================================================
optimizer = tf.keras.optimizers.Adam(lr=0.001)
model = Sequential()

model.add(Dense(60, input_shape = (X_train.shape[1],), activation = 'relu',kernel_initializer='glorot_uniform'))
model.add(Dropout(0.2))
model.add(Dense(60, activation = 'relu',kernel_initializer='glorot_uniform'))
model.add(Dropout(0.2))
model.add(Dense(60, activation = 'relu',kernel_initializer='glorot_uniform'))

model.add(Dense(1,activation = 'linear',kernel_initializer='glorot_uniform'))

model.compile(loss = 'mse', optimizer = optimizer, metrics = ['mse'])

history = model.fit(X_train, y_train, epochs = 100,
                    validation_split = 0.1, shuffle=True, batch_size=250
                    )

history_dict = history.history

loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']

y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)

y_train_pred = denormalize(y_train_pred)
y_test_pred = denormalize(y_test_pred)


plt.figure()
plt.plot((y_test1),(y_test_pred),'.', color='darkviolet', alpha=1, marker='o', markersize = 2, markeredgecolor = 'black', markeredgewidth = 0.1)
plt.plot((np.array((-0.1,7))),(np.array((-0.1,7))),'-', color='magenta')
plt.xlabel('True')
plt.ylabel('Predicted')
plt.title('Test')

plt.figure()
plt.plot((y_train1),(y_train_pred),'.', color='darkviolet', alpha=1, marker='o', markersize = 2, markeredgecolor = 'black', markeredgewidth = 0.1)
plt.plot((np.array((-0.1,7))),(np.array((-0.1,7))),'-', color='magenta')
plt.xlabel('True')
plt.ylabel('Predicted')
plt.title('Train')

plt.figure()
plt.plot(loss_values,'b',label = 'training loss')
plt.plot(val_loss_values,'r',label = 'val training loss')
plt.xlabel('Epochs')
plt.ylabel('Loss Function')
plt.legend()

print("\n\nThe R2 score on the test set is:\t{:0.3f}".format(r2_score(y_test_pred, y_test1)))

print("The R2 score on the train set is:\t{:0.3f}".format(r2_score(y_train_pred, y_train1)))
from sklearn import metrics

# Measure MSE error.  
score = metrics.mean_squared_error(y_test_pred,y_test1)
print("\n\nFinal score test (MSE): %0.4f" %(score))
score1 = metrics.mean_squared_error(y_train_pred,y_train1)
print("Final score train (MSE): %0.4f" %(score1))
score2 = np.sqrt(metrics.mean_squared_error(y_test_pred,y_test1))
print(f"Final score test (RMSE): %0.4f" %(score2))
score3 = np.sqrt(metrics.mean_squared_error(y_train_pred,y_train1))
print(f"Final score train (RMSE): %0.4f" %(score3))

Answer 1

Tensorflow、Keras 和其他深度学习库在幕后处理它。不必为了推理而显式地移除 dropout。 dropout 仅在训练阶段有效。
此外，dropout 只是在每次迭代的相应层中随机丢弃神经元以及传入和传出连接。目的是避免过拟合。它与层的正确或错误输出无关。

Answer 2

我完全同意接受的答案，但我想补充一件事。当你在训练中使用 dropout 时，比如说 10%，那么大约 10% 的神经元将被切断。在测试阶段，你所有的神经元都恢复了，但是层激活将被缩放 0.9（10% 损失）。因为层响应应该与训练阶段相似。