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

Test problem #14

Closed
WeeshawChen opened this issue Dec 19, 2019 · 5 comments
Closed

Test problem #14

WeeshawChen opened this issue Dec 19, 2019 · 5 comments

Comments

@WeeshawChen
Copy link

There is something wrong when I try to test my own dataset, I've already trained my models and now I want to generate a new dataset so I write this command in my terminal :python test.py --phase test --name dimmer --dataroot ./datasets/stanfordcars/test0_day --n_domains 2 --which_epoch 195 --serial_test

@WeeshawChen
Copy link
Author

and it just shows Created 2 Encoder-Decoder pairs
Number of parameters per Encoder: 5099143
Number of parameters per Decoder: 6565770
and nothing happened in my ./results/dimmer/test_195/images
Can you please tell me how to address my problem?

@AAnoosheh
Copy link
Owner

Because the dataloader is the same structure during train and test, you have to give it a dataroot with at least two folders starting with the word "test". (And it will test all N of these folders)

So for you I'm guessing it's just:
--dataroot ./datasets/stanfordcars/

Try that out and let me know.

@WeeshawChen
Copy link
Author

emm, sadly it seems like nothing changed~
my dataset structure is like this:

  • datasets
    • stanfordcars
      -test0_day
      -test1_night
      -train0_day
      -train1_night
      so I write this command in my terminal:
      python test.py --phase test --name dimmer --dataroot ./datesets/stanfordcars/ --n_domains 2 --which_epoch 200 --serial_test
      And the problem is just as same as before~

@AAnoosheh
Copy link
Owner

May or may not be this, but ./datasets is misspelled in your command

@WeeshawChen
Copy link
Author

oh my god.....it worked thanks to you. I am so sorry that I made a stupid typo problem, and I can't express how grateful I am! Thanks a lot! :)

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