About the effect of the code

[zhyhy]

Hello, I tested your code on the MNIST data set and found that the effect is not so good. Can you achieve better open set recognition?

[aadeshnpn]

Thanks @zhyhy . Did you try training a different network on MNIST dataset and evaluate the performance? For me, the classification accuracy was around 97%.

[xiangyangyu]

I also encountered the same problem, using your code to run the performance is very poor, and I see your results in ipynb file are also not really good. Is there a problem somewhere?