Why the directions of digits in visualization are exactly the same?

[maxenceliu]

Not only in your ReadMe, but also in my training results. The directions of each digits in the visualization are exactly same. I think the directions should depend on the random initialization to some extent. So is there are something in your code which caused that?

Thx~

[maxenceliu]

hallo? Really wondering...

[maxenceliu]

oh ,got it. mxnet is different from numpy in function random. numpy use different random seed durning each run however mxnet use same seed....

[maxenceliu]

but still interesting, since during each train ,it use different m, this constraint won't change the final direction however

[luoyetx]

margin won't change the direction. I think the weight initialization makes this.