使用model.predict()与keras一起输出的概率得分 [英] Output Probability score with keras using model.predict()
问题描述
我有一个用于图像分类的cnn模型,该模型使用S型激活函数作为最后一层
I have a cnn model for image classification which uses a sigmoid activation function as its last layer
from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
input_shape=(1500, 1500, 3)))
..........
model.add(layers.Dense(1, activation='sigmoid'))
图像属于两个类别.当我在图像上使用model.predict()
时,我得到0或1.但是,例如,当我使用model.predict_generator()
时,我想要获得像0.656这样的概率得分,则输出这些得分.但是,predict_generator
要求将图像放置在标识其类的文件夹中,因此,它仅与验证和测试有关.我想为一个或多个新的未知图像输出此分数.我该怎么办?
The images belong to two classes. When I use the model.predict()
on an image I get a 0 or a 1. However I want to get a probability score like 0.656 for example when I use model.predict_generator()
, it outputs these scores. However, predict_generator
requires that the images are placed in folders that identify their classes, therefore, it is only relevant for validation and testing. I want to output this score for a new unknown image or images. How can I do this?
推荐答案
我不确定这是否是版本问题,但我确实获得了概率分数.
I'm not sure if this is a version issue, but I do get probability scores.
我使用了一个虚拟网络来测试输出:
I used a dummy network to test the output:
from keras import layers
from keras import models
from keras import __version__ as used_keras_version
import numpy as np
model = models.Sequential()
model.add(layers.Dense(5, activation='sigmoid', input_shape=(1,)))
model.add(layers.Dense(1, activation='sigmoid'))
print((model.predict(np.random.rand(10))))
print('Keras version used: {}'.format(used_keras_version))
产生以下输出:
[[0.252406 ]
[0.25795603]
[0.25083578]
[0.24871194]
[0.24901393]
[0.2602583 ]
[0.25237608]
[0.25030616]
[0.24940264]
[0.25713784]]
Keras version used: 2.1.4
真的很奇怪,您只能得到0和1的二进制输出.特别是当Sigmoid层实际上返回浮点值时.
Really weird that you get only a binary output of 0 and 1. Especially as the sigmoid layer actually returns float values.
我希望这会有所帮助.
这篇关于使用model.predict()与keras一起输出的概率得分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!