Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

pretrain faceset download error #18

Closed
camjac251 opened this issue Feb 23, 2020 · 6 comments
Closed

pretrain faceset download error #18

camjac251 opened this issue Feb 23, 2020 · 6 comments

Comments

@camjac251
Copy link

camjac251 commented Feb 23, 2020

I am trying to run the first step on the DFL colab latest notebook but get this error on the last part of it. DeepFaceLab uses faceset.pak which could simplify things, not needing to unzip etc.

I'll try to figure it out locally and create a pull request

[/content/pretrain_CelebA.zip]
  End-of-central-directory signature not found.  Either this file is not
  a zipfile, or it constitutes one disk of a multi-part archive.  In the
  latter case the central directory and zipfile comment will be found on
  the last disk(s) of this archive.
unzip:  cannot find zipfile directory in one of /content/pretrain_CelebA.zip or
        /content/pretrain_CelebA.zip.zip, and cannot find /content/pretrain_CelebA.zip.ZIP, period.
@camjac251
Copy link
Author

I just tried it again and it worked. Not sure if it was a bug or what

@chervonij
Copy link
Owner

@camjac251
yes, it's problem with gdrive.
I work to fix this

@chervonij
Copy link
Owner

@camjac251
fixed.
now downloads from github.
there should be no problems.

@camjac251
Copy link
Author

camjac251 commented Feb 24, 2020

Oh cool thanks. Would it be possible for some error handling with the download if it fails?

I also think I got an OOM error but it didn't look like a usual one. Is it possible to output friendly error messages if this happens

tcmalloc: large alloc 2017501184 bytes == 0x131d64000 @  0x7f00cbde02a4 0x592727 0x4dddf7 0x4e3200 0x4e284a 0x4e14d8 0x4e2c5b 0x4e30d0 0x4e3ac6 0x5ec117 0x50a9da 0x50c5b9 0x508245 0x50a080 0x50aa7d 0x50c5b9 0x509d48 0x50aa7d 0x50c5b9 0x509d48 0x50aa7d 0x50c5b9 0x508245 0x50a080 0x50aa7d 0x50c5b9 0x508245 0x58958c 0x5a067e 0x50d966 0x509d48

@chervonij
Copy link
Owner

@camjac251
this is github. no errors should be.
even if it does, then training just won't start.

about OOM.
I can do nothing with this.
this is an internal tensorflow error.
I don’t know how to get OOM on Colab, but lower settings of your model.

@chervonij
Copy link
Owner

Solved.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants