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

training problem:IndexError: Cannot choose from an empty sequence #27

Open
Qudagang opened this issue Jul 6, 2019 · 2 comments
Open

Comments

@Qudagang
Copy link

Qudagang commented Jul 6, 2019

when I train using small content dataset, the system puts forward" IndexError: Cannot choose from an empty sequence".

Process Process-1: ValueError: number of bits must be greater than zero:
IndexError: Cannot choose from an empty sequence

Process Process-3:
ValueError: number of bits must be greater than zero;
IndexError: Cannot choose from an empty sequence;

Process Process-7:
ValueError: number of bits must be greater than zero;
IndexError: Cannot choose from an empty sequence;
Processes are started.

Process Process-9:
raise IndexError('Cannot choose from an empty sequence')
IndexError: Cannot choose from an empty sequence

Start training.
[] Reading latest checkpoint from folder ./models\model_van-gogh_new\checkpoint.
[
] Reading latest checkpoint from folder ./models\model_van-gogh_new\checkpoint_long.
[!] Load failed...
0%| | 0/300000 [00:00<?, ?it/s]

Then the train process is always like the lines above.

I don't know the causing problem.

@ofirkris
Copy link

Same issue here, any solution?

@ketan4373
Copy link

ketan4373 commented Aug 18, 2020

I found the problem solution. This happens because the python could not access the content dataset. In my case, I had external drive mounted and docker was not able to access that.

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

3 participants