Skip to content

fix: preserve HME100k prediction case in OCRBench scoring #1278

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.

Sign up for GitHub

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

Merged
kcz358 merged 1 commit into from
Apr 10, 2026
+3 −3
Merged

fix: preserve HME100k prediction case in OCRBench scoring #1278

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions lmms_eval/tasks/ocrbench/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def ocrbench_doc_to_text(doc, lmms_eval_specific_kwargs):


def ocrbench_process_results(doc, results):
pred = results[0].lower().strip()
pred = results[0].strip()
gt_ans = doc["answer"]
dataset_name = doc["dataset"]

Expand Down Expand Up @@ -88,9 +88,9 @@ def ocrbench_aggregate_accuracy(results, args):
print(f"Handwriting Recognition(Total 50): {OCRBench_score['Handwriting Recognition']}", file=f)
print(f"Digit String Recognition(Total 50): {OCRBench_score['Digit String Recognition']}", file=f)
print(f"Non-Semantic Text Recognition(Total 50): {OCRBench_score['Non-Semantic Text Recognition']}", file=f)
print("----------------------------------------------------------------", file=f)
print("-------------------------------------------------------------", file=f)
print(f"Scene Text-centric VQA(Total 200): {OCRBench_score['Scene Text-centric VQA']}", file=f)
print("----------------------------------------------------------------", file=f)
print("----------------------------------------------------------", file=f)
print(f"Doc-oriented VQA(Total 200): {OCRBench_score['Doc-oriented VQA']}", file=f)
print("----------------------------------------------------------------", file=f)
print(f"Key Information Extraction(Total 200): {OCRBench_score['Key Information Extraction']}", file=f)
Expand Down
Loading