Python Keras 报错AttributeError: 'Sequential' object has no attribute 'predict_classes'解决方法
本文文要介绍Python中，使用 Keras 执行yhat_classes = model.predict_classes(X_test)代码报错：AttributeError: 'Sequential' object has no attribute 'predict_classes'解决方法。
示例代码：
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)
问题原因：
在TensorFlow 2.6版本中删除了这个predict_classes函数。
可以使用如下代码：
predict_x=model.predict(X_test) classes_x=np.argmax(predict_x,axis=1)
参考链接：https://www.cjavapy.com/article/2239/
- 39 predict_classes AttributeError Sequential attribute39 predict_classes attributeerror sequential 39 quot attributeerror attribute 39 attributeerror attribute nonetype 39 attributeerror antialias attribute 39 attributeerror tensorflow attribute 39 attributeerror attribute copy_src 39 attributeerror attribute深度 v_flag_cb_issuer_check 39 attributeerror attribute 39 attributeerror attribute模型 39 attributeerror attribute数据