Keras Sequential模型调用predict_proba报错，疑版本问题求助

问题背景 #

你尝试通过以下代码获取分类模型的类别概率：

# example making new probability predictions for a classification problem
from keras.models import Sequential
from keras.layers import Dense
from sklearn.datasets import make_blobs
from sklearn.preprocessing import MinMaxScaler
# generate 2d classification dataset
X, y = make_blobs(n_samples=100, centers=2, n_features=2, random_state=1)
scalar = MinMaxScaler()
scalar.fit(X)
X = scalar.transform(X)
# define and fit the final model
model = Sequential()
model.add(Dense(4, input_shape=(2,), activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(X, y, epochs=500, verbose=0)
# new instances where we do not know the answer
Xnew, _ = make_blobs(n_samples=3, centers=2, n_features=2, random_state=1)
Xnew = scalar.transform(Xnew)
# make a prediction
ynew = model.predict_proba(Xnew)
# show the inputs and predicted outputs
for i in range(len(Xnew)):
    print("X=%s, Predicted=%s" % (Xnew[i], ynew[i]))

运行时出现错误：

AttributeError: 'Sequential' object has no attribute 'predict_proba'

推测是版本更新导致的方法移除。

解决方案 #

在TensorFlow 2.x整合后的Keras版本中，predict_proba方法已被移除，直接使用predict方法即可获取概率值：

• 对于二分类任务（如你的代码中使用sigmoid激活），model.predict(Xnew)会直接返回每个样本属于正类的概率，和原predict_proba的输出完全一致。
• 对于多分类任务（使用softmax激活），predict返回的是每个样本在所有类别上的概率分布，同样可以替代predict_proba。

修改后的核心代码行：

ynew = model.predict(Xnew)

修改后的完整代码 #

# example making new probability predictions for a classification problem
from keras.models import Sequential
from keras.layers import Dense
from sklearn.datasets import make_blobs
from sklearn.preprocessing import MinMaxScaler
# generate 2d classification dataset
X, y = make_blobs(n_samples=100, centers=2, n_features=2, random_state=1)
scalar = MinMaxScaler()
scalar.fit(X)
X = scalar.transform(X)
# define and fit the final model
model = Sequential()
model.add(Dense(4, input_shape=(2,), activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(X, y, epochs=500, verbose=0)
# new instances where we do not know the answer
Xnew, _ = make_blobs(n_samples=3, centers=2, n_features=2, random_state=1)
Xnew = scalar.transform(Xnew)
# make a prediction - 使用predict替代predict_proba
ynew = model.predict(Xnew)
# show the inputs and predicted outputs
for i in range(len(Xnew)):
    print("X=%s, Predicted=%s" % (Xnew[i], ynew[i]))

内容的提问来源于stack exchange，提问作者Phoenix