search

jaanli / variational-autoencoder

Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
https://jaan.io/what-is-variational-autoencoder-vae-tutorial/
MIT License
1.15k stars 256 forks source link

SystemExit #12

Closed Alla-Abdella closed 5 years ago

Alla-Abdella commented 5 years ago

Hi Altosaar,

I run your code on collab.research.google.com and it gave this error: "SystemExit /usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py:2890: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D. warn("To exit: use 'exit', 'quit', or Ctrl-D.", stacklevel=1)"

Can you please run it on colllab ?

Thank you!

jaanli commented 5 years ago

I haven't tested it with colab. Can you split the code according to the whitespace into separate cells in colab? Then link to the colab notebook, highlighting which cell gives an error?

Alla-Abdella commented 5 years ago

Yes, sure. I’ll do it and send it to you.

On Mon, Mar 11, 2019 at 10:21 AM Jaan Altosaar notifications@github.com wrote:

I haven't tested it with colab. Can you split the code according to the whitespace into separate cells in colab? Then link to the colab notebook, highlighting which cell gives an error?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/altosaar/variational-autoencoder/issues/12#issuecomment-471558153, or mute the thread https://github.com/notifications/unsubscribe-auth/ASuwvbfSTRlR8KDXoJviyntdMLWQdBppks5vVmZVgaJpZM4bmbbE .

ExeCuteRunrunrun commented 5 years ago

Hi, Altosaar and alla15747, Did you figure out the problem ? I encountered the same error using a jupyter notebook with a gpu. The error occurs at the last iter of training and says : "Iteration: 99000 ELBO: -82.887 s/iter: 2.607e-03 An exception has occurred, use %tb to see the full traceback. SystemExit" I checked the log directory, it contains all jpg pictures until the 99000th one. Many thanks to you !

jaanli commented 5 years ago

@ExeCuteRunrunrun or @alla15747 can you please share the jupyter notebook?

(and do you need to run for that many iterations? or does the loss plateau.)