Hongxin Wei

Results 10 issues of Hongxin Wei

Hi, In the paper, it writes: "Without assuming such knowledge, we use the maximum softmax probabilities to score anomalies and show that models which are **pre-trained then tuned** provide superior...

I tried to use the code to reproduce some paper on DML, but it has too many configs need to verify. Could you please provide more details?

Hi, Thanks for your great work. I'd like to run the script but I found the [environment.yml](https://github.com/Jingkang50/OpenOOD/blob/main/environment.yml) cannot be directly installed in many GPU machines. The problem might be caused...

看到观察中提到以下两点,想了解下是哪篇paper中的 > 多步负荷预测 > 多任务多输出模型,每步预测对于特征的关注点应该不一样,学习一个feature mapping 的mask attention。 > > 异常数据mask负荷预测 > 在原始feature mapping 后接一个attention,自动mask 异常输入,提升模型的鲁棒性。

I want to run it on kubernetes , anyone try?

There is a sentence in the appendix: "With batch normalization, we effectively cancel the learning rate of Meta-Weight-Net, and it works well with a fixed learning rate. " I'm not...

Hi, Thanks for this great implementation. When I ran this code, I found that the implementation of the NLNL loss might exist a problem that will cause loss to be...

In this repo, "heteroskedastic_cifar.py" contains the code for adding noisy labels in cifar datasets but only has "step"-type imbalance. I tried to use "imbalance_cifar.py" from LDAM to produce experiments on...

MIT takes down 80 Million Tiny Images data set due to racist and offensive content. https://venturebeat.com/2020/07/01/mit-takes-down-80-million-tiny-images-data-set-due-to-racist-and-offensive-content/