CODEWITHSUNDEEP
rneural-networkrstudio-servermxnet
Garglesoap
Garglesoap

Reputation: 575

Strange mxnet behavior in R: results not reproducible

Does mxnet store data/models somewhere outside of R? I keep running into scenarios where the first NN run of the day will produce good results, and every following run (even of the exact same code) will produce NA/NaN for all training steps.

Example: https://github.com/xup6fup/MxNetR-examples/blob/master/1.%20Basic%20models/3.%20softmax%20regression/1.%20Standard%20example.R

I copied and pasted the code as is, ran it and got about 70% accuracy. I noticed that the device was set to cpu, and I have gpu version compiled. So I changed it to gpu, reran ..... all NaN. Clear R session workspace, rerun original code with cpu, all NA.

Restart Rstudio server, rerun exact code.... all NA. It seems like SOMETHING is being stored outside of rstudio server and it interferes with subsequent FeedForward. I have this issue with multiple mxnet tutorials, where often they will work the first time, but subsequently will fail, even with identical code run.

Upvotes: 1

Views: 128

Answers (1)

jeremiedb
jeremiedb

Reputation: 41

If library was compiled somewhere before Nov 12 2017, then there's been a bug present in the random initialisation for some time which resulted in the initialization weights to be all nearly 0s.

Upvotes: 2

Related Questions