Matthew Yeung comments

Repositories
Issues
Comments

Results 14 comments of


                                            Matthew Yeung

I have read the enas paper，which says that weight sharing is used for efficiency. Any one can tell me which part of the code realize the weight sharing?Thanks a lot!

@berisfu its where the reuse=reuse comes in. within the variablescope under ("child") all train, val, test graph use the same parameters.

Install Alpa without GPU

Seems to happen for CUDA build as well here. ``` ... CUDA enabled: yes NCCL enabled: yes ... ``` EDIT: Just to answer myself here, it works for me when...

Which version of mxnet do you use in P3?

Just came across this, you need to checkout the "priority" branch

Question about output value

@zeus7777777 Did you end up fixing that problem, after i added pooling layers at those branches, i got an error regarding the output channels. not sure whether we should *=...