Comments (7)
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.
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.
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.
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.
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.
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.
from interpretdl.
Related Issues (20)
- 运行example_grad_cam_cv.ipynb时报错 HOT 3
- 热力图 HOT 7
- 关于分割模型的可视化 HOT 5
- Infidelity metric not found, probably a new release needed HOT 1
- Interface
- 长宽不相等的图像怎么输入 HOT 5
- Gradient computation changed since paddle2.4
- 分割可视化 HOT 25
- Grad-CAM可视化分割模型 HOT 2
- GradcamSeg是否支持paddle2.4以上版本? HOT 1
- 请问这里边有没有和自然语言处理相关的 HOT 7
- softmax(): argument 'x' (position 0) must be Tensor, but got list HOT 3
- Tutorial error HOT 3
- Failed to apply gradcam on mobileNetv3-large HOT 6
- 在语义分割中应用GradCAM时,如何对整幅图像进行热力图显示,传入的pixels大小如何确定 HOT 2
- 怎么拿出paddledetection中间的某一层进行可视化 HOT 1
- wrong url HOT 2
- UFuncTypeError: Cannot cast ufunc 'add' output from dtype('O') to dtype('float64') with casting rule 'same_kind' HOT 6
- pip install interpretdl ERROR: Failed building wheel for scikit-learn HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from interpretdl.