我正在尝试使用joblib来保存我的神经网络模型，该模型在pandas中使用，准确率达到96%。我的数据集有9列特征，用于预测乳腺癌。

y_train_categorical = to_categorical(y_train)y_test_categorical = to_categorical(y_test)from tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Denseneural_model = Sequential()neural_model.add(Dense(units=6, activation='relu', input_dim=9))neural_model.add(Dense(units=2, activation='softmax')) neural_model.compile(optimizer='adam',              loss='categorical_crossentropy',              metrics=['accuracy'])neural_model = neural_model.fit(    X_train_scaled,    y_train_categorical,    epochs=200,    shuffle=True,    verbose=2)from sklearn.externals import joblib joblib.dump(neural_model, 'neural.pkl') # 也尝试过dump(neural_model, 'neural.joblib')```错误信息: can't pickle _thread.RLock objects

回答：

不建议使用pickle或cPickle来保存Keras模型。

你只需要这样做：model.save(filepath)

更多信息，请查看文档。