Skip to content

[Serve] fix video analysis release test #61324

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
aslonnie merged 2 commits into from
Feb 26, 2026
Merged

[Serve] fix video analysis release test #61324

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0110b7
[Serve] fix video analysis release test
abrarsheikh Feb 25, 2026
d958785
Merge branch 'master' into abrar-vid-analysis-fix
aslonnie Feb 25, 2026
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
5 changes: 2 additions & 3 deletions doc/source/serve/tutorials/video-analysis/deployments/encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,9 +69,8 @@ def encode_frames(self, frames: np.ndarray) -> np.ndarray:
with torch.no_grad():
with torch.amp.autocast(device_type=self.device, enabled=self.device == "cuda"):
outputs = self.model.get_image_features(**inputs)

# L2 normalize on GPU (faster than CPU numpy)
frame_embeddings = torch.nn.functional.normalize(outputs, p=2, dim=1)
# get_image_features returns BaseModelOutputWithPooling; use pooler_output for embeddings
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Feb 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

While the new comment is helpful for understanding the change in the transformers library, the removed comment # L2 normalize on GPU (faster than CPU numpy) provided a useful performance rationale. It would be beneficial to retain this information for future maintainers, especially in a tutorial. Consider combining both pieces of information.

Suggested change
# get_image_features returns BaseModelOutputWithPooling; use pooler_output for embeddings
# get_image_features returns BaseModelOutputWithPooling; use pooler_output for embeddings.
# The embeddings are then L2 normalized on GPU (faster than CPU numpy).

frame_embeddings = torch.nn.functional.normalize(outputs.pooler_output, p=2, dim=1)

# Move to CPU and convert to numpy
result = frame_embeddings.cpu().numpy().astype(np.float32)
Expand Down