访问整个混乱矩阵 [英] Access to entire confusion matrix

问题描述

在使用AutoML Vision训练了图像分类模型之后，评估"选项卡提供了对模型性能的访问，特别是对混淆矩阵的访问.我的数据集有100多个标签，但是混淆矩阵仅显示为10x10矩阵.我的问题:

after training an image classification model using AutoML Vision, the "Evaluate" tab gives access to model performance, specifically to the confusion matrix. My dataset has over 100 labels, but the confusion matrix is only displayed as a 10x10 matrix. My questions:

• 混淆矩阵仅显示最差的性能(例如，超过某个阈值)，还是不考虑性能而将其限制为10x10表示?

• does the confusion matrix only display the worst performances (above a certain threshold for example) or is this limited to a 10x10 representation regardless of performance?

有没有办法访问整个混乱矩阵?

Is there a way to access the entire confusion matrix?

非常感谢！

推荐答案

没关系:阅读 cloud-vision-discuss google组，我找到了答案:您可以通过API获取整个矩阵:

Never mind: after reading through the cloud-vision-discuss google group, I found the answer: you can get the entire matrix through the API: https://cloud.google.com/vision/automl/docs/reference/rest/v1beta1/projects.locations.models.modelEvaluations

这篇关于访问整个混乱矩阵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！