python - Keras: .predict returns percentages instead of classes

Question

I am building a model with 3 classes: [0,1,2] After training, the .predict function returns a list of percentages instead. I was checking the keras documentation but could not figure out, what I did wrong. .predict_classes is not working anymore, and I did not have this problem with previous classifiers. I already tried different activation functions (relu, sigmoid etc.) If I understand correctly, the number inDense(3...) defines the amount of classes.

outputs1=Dense(3,activation='softmax')(att_out) 
model1=Model(inputs1,outputs1)
model1.summary()
model1.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=['accuracy'])
model1.fit(x=text_pad,y=train_y,batch_size=batch_size,epochs=epochs,verbose=1,shuffle=True) 

y_pred = model1.predict(test_text_matrix)

Output example:

[[0.34014237 0.33570153 0.32415614]
 [0.34014237 0.33570153 0.32415614]
 [0.34014237 0.33570153 0.32415614]
 [0.34014237 0.33570153 0.32415614]
 [0.34014237 0.33570153 0.32415614]]

Output I want:

[1,2,0,0,0,1,2,0]

Thank you for any ideas.

标签： pythontensorflowkeras

Answer 1

您没有做错任何事情，predict始终返回模型的输出，对于分类器而言，这始终是每类的概率。

predict_classes仅适用于Sequential模型，不适用于功能模型。

但是有一个简单的解决方案，您只需要argmax在最后一个维度上取，您将获得类索引：

y_probs = model1.predict(test_text_matrix)
y_pred  = np.argmax(y_probs, axis=-1)