Comments (5)
迭代没有变化也是正常的,你不妨换个参数试试?
原代码的出处是作者Mingsheng Long的主页,你可以去看看
from transferlearning.
我又试了一下,原文代码好像没有迭代部分,我的数据Acc=0.9284。而您的代码有一个迭代部分,通过T设置迭代次数,但每次迭代就像我贴的图片一样,没有变化,并且Acc=0.0701(比较离谱)。我对比了一下,在Construct MMD matrix这块,原码有训练一个model。而您的代码没有model,加入了一个N,是希望每次迭代变化吗?但是迭代没有变化,我觉得是代码可能有问题,导致迭代环节没有变化。
from transferlearning.
from transferlearning.
@kind-hearted-Tbag 我刚更新了一下ARTL方法的代码,如果你还在用的话,可以再看一下有没有问题。我是基于我目前正在用的代码做的,应该是可以跑的。
from transferlearning.
非常感谢! 现在好了,就45和51行有点小问题,n_neighbor改为p,mu是多余的。 现在正确率是0.9299(挺好),但每次迭代任然没有变化,是不是所有的数据都这样。这方面我会继续尝试的。
from transferlearning.
Related Issues (20)
- Deep DG HOT 9
- MMD距离 backward问题 HOT 3
- BDA代码中的数据集的问题 HOT 2
- 关于TransferNet中source_clf计算的疑问 HOT 1
- 关于复现 HOT 1
- 对比算法的复现缺少部分流程 HOT 1
- 程序显示没有loss_funcs模块 HOT 1
- Our new test-time adaptation algorithm for segmentation HOT 3
- 关于transferlearning/code /DeepDA的模型代码读取 HOT 2
- How to use DIFEX for single domain generalization? HOT 2
- code add HOT 2
- 有关于在使用DG中DANN方法中遇到的问题
- Office-31 webcam域上微调模型丢失 HOT 1
- 是否需要进行微调? HOT 2
- 作者您好!请问AdaRNN的对比实验中,MMD-RNN和DANN-RNN是如何实现的,MMD-RNN的源域和目标域是如何定义的,AdaRNN相比这两个对比模型进步在哪里? HOT 1
- Feature Request:添加ADDA的代码以及与其他方法的比较。 HOT 1
- 王老师您好,Domain Generalization for Activity Recognition via Adaptive Feature Fusion请问这篇论文的代码具体在哪个文件夹里?找了很久没找到 HOT 1
- Time series domain adaptation benchmark and datasets HOT 1
- DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization中的cross_dataset的文件 HOT 1
- BDA中A-distance问题
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 transferlearning.