second commit

This commit is contained in:
lzy
2025-05-28 10:55:34 +08:00
parent 0f80316f8b
commit ef9355f2f5
73 changed files with 485583 additions and 0 deletions

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,15 @@
import json
with open("/home/ubuntu/50T/fsy/benchmark/ScienceQA/ScienceQA-mat.json", 'r', encoding='utf-8') as f:
data = json.load(f)
filtered_data = {}
for key, item in data.items():
if item.get("image") is None:
filtered_data[key] = item
with open("/home/ubuntu/50T/fsy/benchmark/ScienceQA/filtered_output.json", 'w', encoding='utf-8') as f:
json.dump(filtered_data, f, ensure_ascii=False, indent=4)
print(f"筛选完成,共筛选出 {len(filtered_data)} 条数据,并保存在 'filtered_output.json' 文件中。")