Skip to content

feat: add process_results_use_image and video metadata dict support in task API #1275

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
Luodian merged 1 commit into from
Apr 11, 2026
+29 −16
Merged

feat: add process_results_use_image and video metadata dict support in task API #1275

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
45 changes: 29 additions & 16 deletions lmms_eval/api/task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1157,21 +1157,24 @@ def concat_tar_parts(tar_parts, output_tar):
if split in [self.config.training_split, self.config.validation_split, self.config.test_split, self.config.fewshot_split]:
self.dataset[split] = self.config.process_docs(self.dataset[split])

# copy dataset, remove image features
self.dataset_no_image = self.dataset.copy()
for doc_name in self.dataset_no_image:
remove_cols = []
features = self.dataset_no_image[doc_name].features
# If it is an Image instance or a Sequence of Image instance. Remove it
for feature in features:
if isinstance(features[feature], Image):
remove_cols.append(feature)
elif isinstance(features[feature], Sequence) and isinstance(features[feature].feature, Image):
remove_cols.append(feature)
elif isinstance(features[feature], Audio):
remove_cols.append(feature)
for remove_col in remove_cols:
self.dataset_no_image[doc_name] = self.dataset_no_image[doc_name].remove_columns(remove_col)
# copy dataset, remove image features (unless process_results needs them)
if getattr(self.config, "process_results_use_image", False):
self.dataset_no_image = self.dataset
else:
self.dataset_no_image = self.dataset.copy()
for doc_name in self.dataset_no_image:
remove_cols = []
features = self.dataset_no_image[doc_name].features
# If it is an Image instance or a Sequence of Image instance. Remove it
for feature in features:
if isinstance(features[feature], Image):
remove_cols.append(feature)
elif isinstance(features[feature], Sequence) and isinstance(features[feature].feature, Image):
remove_cols.append(feature)
elif isinstance(features[feature], Audio):
remove_cols.append(feature)
for remove_col in remove_cols:
self.dataset_no_image[doc_name] = self.dataset_no_image[doc_name].remove_columns(remove_col)

def has_training_docs(self) -> bool:
if self.config.training_split is not None:
Expand Down Expand Up @@ -1766,7 +1769,17 @@ def auto_doc_to_messages(doc):
if isinstance(visual, PIL_Image.Image):
content.append({"type": "image", "url": visual})
elif isinstance(visual, dict):
content.append({"type": "audio", "url": visual})
# Dict visuals carry explicit type (default: video).
# Metadata keys (video_start, video_end, etc.) are
# preserved in the url field so they flow through
# ChatVideoContent → extract_media → fetch_video.
media_type = visual.get("type", "video")
has_metadata = any(k in visual for k in ("video_start", "video_end"))
if has_metadata:
media_url = visual # pass full dict as url
else:
media_url = visual.get("url") or visual.get("path") or visual
content.append({"type": media_type, "url": media_url})
elif isinstance(visual, str):
ext = os.path.splitext(visual)[1].lower()
if ext in _IMAGE_EXTS:
Expand Down
Loading