旅游网站的广告预算怎么做/seo高手培训

这个示例演示如何使用LIME解释CNN的分类问题[1]。

This demo shows how to interpret the classification by CNN using LIME (Local Interpretable Model-agnostic Explanations) [1].

这个演示是基于文献[1]创建的，但具体实现可能与它的正式实现略有不同。

This demo was created based on [1], but the implementation might be a little bit different from its official one.

此代码突出显示了促成分类的区域。

This code highlights the regions that contributed to the classification.

它可以帮助您解释和改进模型，或者，如果突出显示的区域与真正的类无关，您可以重新改进不可信的分类器。

It helps you interpret and improve the model, or, you can recoginize the classifier is not untrustworthy for you if the region highlighted is irrelevant for the true class.

这个演示展示了一个ResNet-18的预先训练模型的例子[2]。

This demo shows the example with a pre-trained model of ResNet-18 [2].

请根据您的网络修改此代码。

Please modify this code based on your network.

LIME可以用于任何类型的数据，这个例子展示了图像分类的代码。

LIME can be utilized for any type of data and this example shows the code for image classification.

参考文献：

[1] Ribeiro, M.T., Singh, S. and Guestrin, C., 2016, August. " Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).

[2] He, K., Zhang, X., Ren, S. and Sun, J., 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

更多精彩文章请关注公众号：