time_iter

@Chenxingyu1990 你可以分享一下你是用的分类器模型吗，我使用f-CLSWGAN获得的模型存在一些问题

I meet the same problem, on all of these five datasets, when unseen grows up seen keeps low level @Chenxingyu1990

[awa1.log](https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning/files/6145611/awa1.log) [sun.log](https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning/files/6145612/sun.log) [flo.log](https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning/files/6145613/flo.log) [awa2.log](https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning/files/6145614/awa2.log) [cub.log](https://github.com/Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning/files/6145615/cub.log) these are training logs, I didn't modify your code except the data path and save every

 this is the visualization results on awa1

could you share the python env or conda env of this project

Thanks for your sincerely help，the problem has been solved. I have a suggestion that you put your environment and datasets links in the readme document. By doing this some misunderstanding...