GithubHelp home page GithubHelp logo

sv-x-softmax's People

Contributors

xiaobocasia avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

sv-x-softmax's Issues

SV-X-Softmax源码

您好!我现在仍然没看到SV-X-Softmax的源码,请问您在哪里公开的呢?

Training from scratch issues

I have reimplemented the SVX-loss function in tensorflow and I've made unit tests to verify the correct behaviour of it. However, when I train a Resnet50 architecture from scratch using SVX loss and MS1Mv2 dataset (the purged one) the loss diverges rapidly. Have you experienced something similar? Any recommendation or idea?

do i need to modify softmax function?

你好,我结合arcface修改了fc7层,请问softmax 还需要修改吗?
hi,i modified fc7,do i need to modify softmax function?

new_zy = mx.sym.where(cond, new_zy, zy_keep)#>0 s*cos(@+m), <0 cut
diff = new_zy - zy#为了将真实的标签位置替换为new_zy
diff = mx.sym.expand_dims(diff, 1)

new_zy = mx.sym.expand_dims(new_zy, 1)
gt_one_hot_down = mx.sym.one_hot(gt_label, depth = args.num_classes, on_value = 0.0, off_value = 1.0)
gt_zy = mx.sym.broadcast_mul(gt_one_hot_down,fc7)#求非gt的Cos值

gt_greater = mx.sym.broadcast_greater(gt_zy,new_zy)#得到非gt值比gt值大的标签索引
gt_lesser_than = mx.sym.broadcast_lesser_equal(gt_zy,new_zy)#得到非gt值小或等于gt值的标签索引
gt_greater_mul = gt_greater*t#非gt位置*t
gt_greater_mul = mx.sym.broadcast_add(gt_greater_mul,gt_lesser_than)#再加上gt_lesser_than,为了与gt_zy相乘
fc7 = mx.sym.broadcast_mul(fc7,gt_greater_mul)#对应位置乘t
gt_greater_add = gt_greater*(t-1)#对应位置变为t-1
fc7 = mx.sym.broadcast_add(fc7,gt_greater_add)#对应位置加上t-1   

gt_one_hot = mx.sym.one_hot(gt_label, depth = args.num_classes, on_value = 1.0, off_value = 0.0)
body = mx.sym.broadcast_mul(gt_one_hot, diff)
fc7 = fc7+body  

SV-cosface不收敛

你好,我实现了一下SV-cosface,但是调节t的时候发现t越大越难收敛效果越差,而且没有t=1时候效果好。其他参数设置都是一样的,请问你们这个SV系列调参有什么策略么?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.