Giter VIP home page Giter VIP logo

Comments (7)

AprilDomLin avatar AprilDomLin commented on May 22, 2024 1

shap:https://github.com/slundberg/shap。

之前有用过 这个他主要依赖于pytorch和TensorFlow的库,计算shapely value。可以用于多种机器学习的模型和深度学习模型。

btw,之前有在知乎看到过张拳石老师团队的研究,好像说可以加快在DL中shapely value 的计算。因为不是主要研究解释性的,所以没有挖掘细节。

from interpretdl.

holyseven avatar holyseven commented on May 22, 2024

暂时没有shapley的。shapley因为在图像方面计算量较大,最开始并没有计划实现。

模型是什么模型呢?用LIME应该都可以解释,不同的模型有不同的算法可以进行解释。

from interpretdl.

AprilDomLin avatar AprilDomLin commented on May 22, 2024

暂时没有shapley的。shapley因为在图像方面计算量较大,最开始并没有计划实现。

模型是什么模型呢?用LIME应该都可以解释,不同的模型有不同的算法可以进行解释。

是用的ViT做的分类模型。主要想尝试做解释分析,但是最近看shapely比较多,所以想尝试一下效果。但是我看shap这个库,是可以支持shapely图像的解释欸。
哈哈哈,非常感谢,我再研究一下解释分析吧。

from interpretdl.

holyseven avatar holyseven commented on May 22, 2024

vanilla ViT结构的话,可以看看这个是否有帮助:https://github.com/PaddlePaddle/InterpretDL/blob/master/examples/example_bt_ga_cv_ViT.ipynb

shapley我们这边再调研和评估一下,要是你有什么想法或者试过哪个算法感觉效果不错,也可以跟分享一下~

from interpretdl.

AprilDomLin avatar AprilDomLin commented on May 22, 2024

这个demo的两个解释方法好像存在问题。报错:AttributeError: 'NoneType' object has no attribute 'numpy'。

我看代码问题,好像是因为注册的hook在backward之前,导致block_attns里面的Tesnor就不存在梯度了。

from interpretdl.

holyseven avatar holyseven commented on May 22, 2024

我这边没有问题,可以正常运行。Paddle版本:2.3.2

Paddle版本可能出现的问题查看:#51

from interpretdl.

AprilDomLin avatar AprilDomLin commented on May 22, 2024

from interpretdl.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.