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

Return empty OrderedDict() when testing #10

Open
Michel-liu opened this issue Dec 24, 2023 · 4 comments
Open

Return empty OrderedDict() when testing #10

Michel-liu opened this issue Dec 24, 2023 · 4 comments

Comments

@Michel-liu
Copy link

Hi~ Thanks for your work. When I try to evaluate the performance of the pretrain ckpt, I got the empty OrderedDict() as follows,
image

I have tried the following evaluation commands,
bash scripts/test.sh config/ESTS/ESTS_5scale_pretrain.py ./datasets 0 ./pretrain.pth totaltext_val,
bash scripts/test.sh config/ESTS/ESTS_5scale_pretrain.py ./datasets 1 ./pretrain.pth totaltext_val,
bash scripts/test.sh config/ESTS/ESTS_5scale_tt_finetune.py ./datasets 0 ./pretrain.pth totaltext_val
and
bash scripts/test.sh config/ESTS/ESTS_5scale_tt_finetune.py ./datasets 0 ./pretrain.pth totaltext_val,
all failed.

@mxin262
Copy link
Owner

mxin262 commented Dec 27, 2023

Hi, is the path for the GT and lexicon correct?

@Michel-liu
Copy link
Author

Hi~ My directory structure is as follows:
image
image

I didn't modify the paths for GT or lexicon settings. I just put the totaltext dataset in ./datasets and ran the evaluation code.
image

How can I link the GT or lexicon path with the evaluation code? Thanks!

@mxin262
Copy link
Owner

mxin262 commented Dec 28, 2023

Hi~, I update the evaluation. You can fix this by updating the this file.

@ASmalFish
Copy link

Has this problem been solved?
I also encountered the same problem

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