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

bleu does not exist #26

Open
jiangsufirstlove opened this issue Feb 13, 2025 · 11 comments
Open

bleu does not exist #26

jiangsufirstlove opened this issue Feb 13, 2025 · 11 comments

Comments

@jiangsufirstlove
Copy link

FileNotFoundError: Couldn't find a module script at /data1/doc_data/ysh/OmniDocBench/bleu/bleu.py. Module 'bleu' doesn't exist on the Hugging Face Hub either.

@jiangsufirstlove
Copy link
Author

Hello! Thank you for your contribution! I'd like to ask you what is the reason for this error reported when I'm doing a formula assessment and bleu is selected in the metrics

@ouyanglinke
Copy link
Collaborator

Please check the version of evaluate.

pip list | grep evaluate
# output: evaluate                  0.4.3

@jiangsufirstlove
Copy link
Author

(omnidocbench) ysh@ubuntu:/data1/doc_data/ysh/OmniDocBench$ pip list | grep evaluate
evaluate 0.4.3
That's the same version I have.

@ouyanglinke
Copy link
Collaborator

Can you show me your end2end.yaml?

@jiangsufirstlove
Copy link
Author

recogition_eval:
metrics:
- Edit_dist
- CDM
#- BLEU
dataset:
dataset_name: omnidocbench_single_module_dataset
ground_truth:
data_path: /data1/doc_data/ysh/OmniDocBench/scripts/eval_formulas8.jsonl
data_key: latex
category_filter: ['equation_isolated']
prediction:
data_key: pred_latex
category_type: formula
that is it

@jiangsufirstlove
Copy link
Author

end2end.yaml
end2end_eval:
metrics:
text_block:
metric:
- Edit_dist
- BLEU
- METEOR
display_formula:
metric:
- Edit_dist
- CDM
table:
metric:
- TEDS
- Edit_dist
reading_order:
metric:
- Edit_dist
dataset:
dataset_name: end2end_dataset
ground_truth:
data_path: ./demo_data/omnidocbench_demo/OmniDocBench_demo.json
prediction:
data_path: ./demo_data/end2end
match_method: quick_match
# filter:
# language: english

@ouyanglinke
Copy link
Collaborator

Please check your proxy. It's HTTPS connection issue. Make sure you can connect HuggingFace.

@jiangsufirstlove
Copy link
Author

jiangsufirstlove commented Feb 13, 2025 via email

@xsank
Copy link

xsank commented Feb 27, 2025

Please check your proxy. It's HTTPS connection issue. Make sure you can connect HuggingFace.

I could connect to the HF, but still with the same problem...

@ouyanglinke
Copy link
Collaborator

You can download BLEU from Huggingface.

Then change the code in

bleu = evaluate.load("bleu", keep_in_memory=True, experiment_id=random.randint(1,1e8))
to

bleu = evaluate.load('/your/download/path/')

@jiangsufirstlove
Copy link
Author

jiangsufirstlove commented Feb 27, 2025 via email

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