[英]How to use keras predict_proba to output 2 columns of probability?
I use this code to predict the probability of 0 and 1 in x_test
, but the result is only one column of probability.我使用这段代码来预测x_test
中 0 和 1 的概率,但结果只有一列概率。 I really don't know whether the probability of this column is the probability of 0 or the probability of 1.真不知道这个列的概率是0的概率还是1的概率。
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
data_train = np.array([
[0, 0, 0],
[0, 1, 0],
[0, 2, 0],
[0, 3, 0],
[1, 0, 0],
[2, 0, 0],
[3, 0, 0],
[1, 1, 1],
[2, 1, 1],
[1, 2, 1],
[3, 1, 1],
])
data_test = np.array([
[1, 3],
[0, 4],
[5, 0]
])
x_train = data_train[:, :-1]
y_train = data_train[:, -1]
x_test = data_test
model = Sequential()
model.add(Dense(512, activation='relu', input_dim=2))
model.add(Dense(200, activation='relu'))
model.add(Dense(200, activation='relu'))
model.add(Dense(128, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['binary_accuracy'])
model.fit(x_train, y_train, epochs=5, batch_size=1, verbose=1)
predict = model.predict_proba(x_test, batch_size=1)
print(predict)
And the result is only 1 column:结果只有 1 列:
[[0.9431795]
[0.47065434]
[0.08615088]]
I want 2 columns of probability, the first column is the probability of 0, and the second column is the probability of 1, such as this:我要2列概率,第一列是0的概率,第二列是1的概率,比如这样:
[[0.23334,0.76267]
……
[0.84984,0.15685]
[0.16663,0.83291]]
How to fix it?如何解决?
First, you need to convert y_train
to one-hot encoding by首先,您需要将y_train
转换为 one-hot encoding
from sklearn.preprocessing import LabelEncoder
from keras.utils import np_utils
encoder = LabelEncoder()
encoder.fit(y_train)
encoded_y = encoder.transform(y_train)
y_train = np_utils.to_categorical(encoded_y)
running this code, y_train
will become运行此代码, y_train
将变为
array([[1., 0.],
[1., 0.],
[1., 0.],
[1., 0.],
[1., 0.],
[1., 0.],
[1., 0.],
[0., 1.],
[0., 1.],
[0., 1.],
[0., 1.]], dtype=float32)
Secondly, you need to change the output layer to其次,您需要将输出层更改为
model.add(Dense(2, activation='softmax'))
with these two modifications, you will get the desired output.通过这两个修改,您将获得所需的输出。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.