简体繁体 English

CNN 音频分类器训练了 3 个类，预测的总和应该小于 1

[英]CNN audio classifier trained with 3 classes and the sum of the prediction should be less than one

原文 2020-04-13 20:28:36 3 1 python/ keras/ classification/ cnn

I built a CNN audio classifier with 3 classes.我构建了一个包含 3 个类的 CNN 音频分类器。 My problem is that their are more than 3 classes, eg a fourth could be "noise".我的问题是他们的课程超过 3 个，例如第四个可能是“噪音”。 So when I call be prediction the sum of these 3 classes is always 1.因此，当我称之为预测时，这 3 个类的总和始终为 1。

prediction = model.predict([X])

Is it somehow possible to extract the accuracy of each class so the sum of these accuracies is less then 1?是否可以以某种方式提取每个 class 的精度，因此这些精度的总和小于 1？

1 个解决方案

If you use a softmax activation function you are forcing the outputs to sum to 1, thereby making a relative confidence score between your classes.如果您使用 softmax 激活 function 您将强制输出总和为 1，从而在您的类之间产生相对置信度得分。 Perhaps, without knowing more about your data and application, a "1 vs all" type scheme would work better for your purposes.也许，在不了解您的数据和应用程序的情况下，“1 vs all”类型的方案会更好地满足您的目的。 For example, each class could have a sigmoid activation function and you could pick the highest prediction but if that prediction doesn't score high enough on a sensitivity threshold then none of the classes are predicted and as such is empty or implicitly "noise."例如，每个 class 可能有一个 sigmoid 激活 function 并且您可以选择最高预测，但如果该预测在灵敏度阈值上得分不够高，则不会预测任何类，因此是空的或隐含的“噪声”。

3 类预测 CNN 深度学习 - 3 Classes prediction CNN Deep Learning

为什么我的 CNN 预训练图像分类器过拟合？ - Why is my CNN pre trained image classifier overfitting?

避免对未使用 CNN 训练的输入进行预测 - Avoid giving prediction for input which is not trained using CNN

CNN Classifier 只猜一件事——PyTorch - CNN Classifier only guesses one thing - PyTorch

为什么投票分类器的准确性低于做出它的单个预测器之一 - Why the voting classifier has less accuracy than one of the individual predictors that made it

如何检查keras分类器/神经网络的训练类？ - how to check the classes a keras classifier/Neural Network is trained on?

Keras给出的准确性低于任何分类器 - Keras give less accuracy than any classifier

使训练有素的分类器仅从已对其进行训练的其他类别中的一组类别进行预测 - Making a trained classifier predict only from a set of classes out of the other classes for which it has been trained

SVC 分类器到 Keras CNN 具有区分未训练类的概率或置信度 - SVC Classifier to Keras CNN with probabilities or confidence to distinguish untrained classes

将两个预训练模型与 2 个不同的类（数据集）结合起来进行预测 - Combining two Pre Trained models with 2 different classes (dataset) for Prediction

暂无

暂无

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.

相关问题 3 类预测 CNN 深度学习 - 3 Classes prediction CNN Deep Learning 为什么我的 CNN 预训练图像分类器过拟合？ - Why is my CNN pre trained image classifier overfitting? 避免对未使用 CNN 训练的输入进行预测 - Avoid giving prediction for input which is not trained using CNN CNN Classifier 只猜一件事——PyTorch - CNN Classifier only guesses one thing - PyTorch 为什么投票分类器的准确性低于做出它的单个预测器之一 - Why the voting classifier has less accuracy than one of the individual predictors that made it 如何检查keras分类器/神经网络的训练类？ - how to check the classes a keras classifier/Neural Network is trained on? Keras给出的准确性低于任何分类器 - Keras give less accuracy than any classifier 使训练有素的分类器仅从已对其进行训练的其他类别中的一组类别进行预测 - Making a trained classifier predict only from a set of classes out of the other classes for which it has been trained SVC 分类器到 Keras CNN 具有区分未训练类的概率或置信度 - SVC Classifier to Keras CNN with probabilities or confidence to distinguish untrained classes 将两个预训练模型与 2 个不同的类（数据集）结合起来进行预测 - Combining two Pre Trained models with 2 different classes (dataset) for Prediction

相关标签

粤ICP备18138465号 © 2020-2024 STACKOOM.COM