欢迎来到尧图网

客户服务 关于我们

您的位置:首页 > 新闻 > 焦点 > 各种CNN 卷积特征图可视化理解方法(链接)

各种CNN 卷积特征图可视化理解方法(链接)

2025/2/3 20:25:44 来源:https://blog.csdn.net/Vertira/article/details/145406254  浏览:    关键词:各种CNN 卷积特征图可视化理解方法(链接)

1.链接一 C/DNN Explainer

CNN Explainerhttps://poloclub.github.io/cnn-explainer/

2.Scaling Deep Learning Interpretability by Visualizing Activation and Attribution

Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationshttps://fredhohman.com/summit/

3.Interactively Deciphering Adversarial Attacks on Deep Neural Networks

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networkshttps://poloclub.github.io/bluff/

4.Visual Analytics in Deep Learning

Visual Analytics in Deep Learning – Visual Analytics in Deep Learninghttps://fredhohman.com/visual-analytics-in-deep-learning/

 

5.GAN Lab

GAN Lab: Play with Generative Adversarial Networks in Your Browser!https://poloclub.github.io/ganlab/

6.Diffusion Explainer:

Diffusion Explainer: Stable Diffusion Explained with Visualizationhttps://poloclub.github.io/diffusion-explainer/

7.

Fred Hohman - ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentationhttps://fredhohman.com/papers/shapeshop

8.Exploring Transformer Models with Interactive Visualization

Dodriohttps://poloclub.github.io/dodrio/

 

 9.Facebook Deep Neural Network Models

ActiVishttps://minsuk.com/research/activis/

 

 

版权声明:

本网仅为发布的内容提供存储空间,不对发表、转载的内容提供任何形式的保证。凡本网注明“来源:XXX网络”的作品,均转载自其它媒体,著作权归作者所有,商业转载请联系作者获得授权,非商业转载请注明出处。

我们尊重并感谢每一位作者,均已注明文章来源和作者。如因作品内容、版权或其它问题,请及时与我们联系,联系邮箱:809451989@qq.com,投稿邮箱:809451989@qq.com