Comments (2)
and also, i think this line:
loss = loss/(4d4)
should be:
loss = loss/(4dd)
from transferlearning.
For the first problem, it is right as:
xm = torch.mean(source, 1, keepdim=True) - source.
Please note that C S (C T ) denote the feature covariance matrices not sample covariance, and you should focus on the covariance between feature.
For the second problem, you are right. As the original paper, it should be loss = loss/(4dd). Besides, the coral code come from another repository, and I did not find this error. Thank for your questions.
from transferlearning.
Related Issues (20)
- 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
- 关于DANN中的域鉴别器的域分类准确率 HOT 2
- 403 ERROR for DeepDG Dataset PACS HOT 2
- 是否有时间序列相关的代码库
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.