Skip to content

Conversation

@jianwensong
Copy link
Contributor

No description provided.

dec_d = {
"file_name": dec_seq["file_names"][e],
"file_origin": d[e]["file_name"],
"file_origin": d[0]["file_name"],
Copy link
Collaborator

Choose a reason for hiding this comment

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

@jianwensong Is this change necessary?
I forgot which case was, but I remeber there was a case we still need access with an index.
Would you please confirm this?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I think it is necessary (at least under current remote inference settings). When the batch size is one, each 'd' enumerated from the 'dataloader' is a list containing one dictionary. If we set it to d[e], remote inference will result in an error. I think only the case where batch size is larger than one may need access this index. But I am not sure whether remote inference always uses batch size 1 or if it supports larger batch sizes.

@fracape fracape merged commit 4fb20be into InterDigitalInc:main Oct 23, 2025
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants