sv-x-softmax's People
Forkers
runauto frizy-up gracejary huacuo xysong1201 maryhh pgsrv tenglied jasonjjl superhero1991 chewkokwah clhne young1403 tony109060581 shz0519 nothingeasy yan-song quasarlight mldl jomplomsv-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?
There is no code files of this repo?
why this repo is empty.
one of the variables needed for gradient computation has been modified by an inplace operation: which is output 0 of MmBackward, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
Hi, I tried your MV-AM and MV-Arc , both give me this error. Someone encountered the same error?
Cloud you share your MS-Celeb-1M-v1c-R dataset.
Hi, could you share your link to download the MS-Celeb-1m-v1c-R dataset?
Or could you please tell us that which datasets are excluded from the original MS-Celeb-1m-v1c,
Thank you
the code is ready?
the code is ready to open source?
Will the Caffe version be released?
Thanks!
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.