Keras:.predict 返回百分比而不是类 [英] Keras: .predict returns percentages instead of classes
问题描述
我正在构建一个包含 3 个类的模型:[0,1,2]
训练后, .predict
函数返回一个百分比列表.我正在检查 keras 文档,但无法弄清楚我做错了什么..predict_classes
不再工作了,我以前的分类器没有这个问题.我已经尝试过不同的激活函数(relu、sigmoid 等)如果我理解正确,Dense(3...)
中的数字定义了类的数量.
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)
输出示例:
[[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]]
我想要的输出:
[1,2,0,0,0,1,2,0]
感谢您的任何想法.
推荐答案
您没有做错任何事,predict
始终返回模型的输出,对于分类器而言,这始终是每个的概率班级.
You did not do anything wrong, predict
has always returned the output of the model, for a classifier this has always been probabilities per class.
predict_classes
仅适用于 Sequential
模型,不适用于功能模型.
predict_classes
is only available for Sequential
models, not for Functional ones.
但是有一个简单的解决方案,你只需要在最后一个维度上取argmax
,你就会得到类索引:
But there is an easy solution, you just need to take the argmax
on the last dimension and you will get class indices:
y_probs = model1.predict(test_text_matrix)
y_pred = np.argmax(y_probs, axis=-1)
这篇关于Keras:.predict 返回百分比而不是类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!