Keras AttributeError: 'Sequential' 对象没有属性 'predict_classes' [英] Keras AttributeError: 'Sequential' object has no attribute 'predict_classes'

问题描述

我正在尝试按照本指南查找模型性能指标(F1 分数、准确率、召回率)https://machinelearningmastery.com/how-to-calculate-precision-recall-f1-and-more-for-deep-learning-models/

Im attempting to find model performance metrics (F1 score, accuracy, recall) following this guide https://machinelearningmastery.com/how-to-calculate-precision-recall-f1-and-more-for-deep-learning-models/

这个确切的代码几个月前还可以使用，但现在返回各种错误，非常令人困惑，因为我没有更改此代码的一个字符.也许包更新改变了一些事情?

This exact code was working a few months ago but now returning all sorts of errors, very confusing since i havent changed one character of this code. Maybe a package update has changed things?

我用model.fit拟合了序列模型，然后用model.evaluate找到了测试精度.现在我正在尝试使用 model.predict_classes 进行类预测(模型是一个多类分类器).代码如下:

I fit the sequential model with model.fit, then used model.evaluate to find test accuracy. Now i am attempting to use model.predict_classes to make class predictions (model is a multi-class classifier). Code shown below:

model = Sequential()
model.add(Dense(24, input_dim=13, activation='relu'))
model.add(Dense(18, activation='relu'))
model.add(Dense(6, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

-

history = model.fit(X_train, y_train, batch_size = 256, epochs = 10, verbose = 2, validation_split = 0.2)

-

score, acc = model.evaluate(X_test, y_test,verbose=2, batch_size= 256)
print('test accuracy:', acc)

-

yhat_classes = model.predict_classes(X_test)
 

最后一行返回错误AttributeError: 'Sequential' object has no attribute 'predict_classes'"

last line returns error "AttributeError: 'Sequential' object has no attribute 'predict_classes'"

这个确切的代码不久前还在工作，所以有点挣扎，感谢您的帮助

This exact code was working not long ago so struggling a bit, thanks for any help

推荐答案

此功能已在 TensorFlow 2.6 版中删除.根据 keras in rstudio 参考

This function were removed in TensorFlow version 2.6. According to the keras in rstudio reference

更新到

predict_x=model.predict(X_test) 
classes_x=np.argmax(predict_x,axis=1)

或者使用 TensorFlow 2.5 或更高版本.

如果您使用的是 TensorFlow 2.5 版，您将收到以下警告:

If you are using TensorFlow version 2.5, you will receive the following warning:

tensorflowpythonkerasenginesequential.py:455: UserWarning: model.predict_classes() 已弃用，将在 2021-01-01 后移除.请改用:* np.argmax(model.predict(x), axis=-1)，如果您的模型进行多类分类(例如，如果它使用 softmax 最后一层激活.* (model.predict(x) > 0.5).astype(int32")，如果您的模型进行二元分类(例如，如果它使用 sigmoid 最后一层激活).

tensorflowpythonkerasenginesequential.py:455: UserWarning: model.predict_classes() is deprecated and will be removed after 2021-01-01. Please use instead:* np.argmax(model.predict(x), axis=-1), if your model does multi-class classification (e.g. if it uses a softmax last-layer activation).* (model.predict(x) > 0.5).astype("int32"), if your model does binary classification (e.g. if it uses a sigmoid last-layer activation).

这篇关于Keras AttributeError: 'Sequential' 对象没有属性 'predict_classes'的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！