Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion vlmeval/dataset/image_vqa.py
Original file line number Diff line number Diff line change
Expand Up @@ -4048,7 +4048,7 @@ class MathCanvas(ImageBaseDataset):
"https://huggingface.co/datasets/shiwk24/MathCanvas-Bench/resolve/main/MathCanvas_Bench_VLMEvalKit.tsv"
}
DATASET_MD5 = {
"MathCanvas-Bench": "9fd0b783ca416dbb20ecfb04d2711411"
"MathCanvas-Bench": "827dd1b1ce9c17d2b8338af6a13b6791"
}

HINT = (
Expand Down
7 changes: 3 additions & 4 deletions vlmeval/dataset/utils/mathcanvas.py
Original file line number Diff line number Diff line change
Expand Up @@ -233,15 +233,14 @@ def summarize_mathcanvas_results(all_results: List[Dict]):
stats['overall']['completely_correct_count'] += 1

# 2. Image Presence Stats
q_images = [p for p in item.get("question_interleave", []) if p['type'] == 'image']
q_images = item.get("image", [])
image_presence_key = "Has Image" if len(q_images) > 0 else "No Image"
_update_stats(stats['by_question_image_count'], image_presence_key, score)

# 3. Knowledge Stats
# Use the primary knowledge area for categorization.
knowledges = item.get("knowledges", [])
knowledge_key = knowledges[0] if knowledges else "Unknown"
_update_stats(stats['by_knowledge'], knowledge_key, score)
category = item.get("category", "Unknown")
_update_stats(stats['by_knowledge'], category, score)

# --- Final Report Generation ---
def calculate_accuracy(data_dict):
Expand Down
Loading