求助：unrolled lstm 如何对输入层共享使用batch norm的aux_states参数

[quanzongfeng]

对于unrolled lstm， 假设序列长度为m， 则将recurrent部门展开有m个input和output， 对input使用batchnorm， 则会建立m个batchnorm节点。
在GrapExecutor：：InitDataEntryInfo函数中， 会根据节点数建立op_nodes， 每个op_nodes处按照op->ListAuxiliaryStates()的数量建立aux_states， 则会建立m个aux_states。

如果希望m个batchnorm像lstm参数一样进行共享，那么如何操作才能使得m个aux_states共享呢？

[winstywang]

Could you revise your questions in English? Since we still have many users who cannot understand Chinese.

[mli]

does this link help? https://github.com/dmlc/mxnet-notebooks/blob/master/python/rnn/lstm.ipynb

[antinucleon]

@mu not really, LSTM Bn problem need to be fixed after nnvm
On Fri, Aug 19, 2016 at 20:40 Mu Li notifications@github.com wrote:

does this link help?
https://github.com/dmlc/mxnet-notebooks/blob/master/python/rnn/lstm.ipynb

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
#3076 (comment), or mute
the thread
https://github.com/notifications/unsubscribe-auth/ABM13jl7tIuvc8fsRy8kcRia0paGIWFUks5qhncwgaJpZM4JoYGw
.

Sent from mobile phone

[horserma]

I have the same problem. How to share the auxiliary states and weights of BatchNorm layer?

[yajiedesign]

This issue is closed due to lack of activity in the last 90 days. Feel free to reopen if this is still an active issue. Thanks!