Add skip-raw-tensors property to gvaclassify and related components#780
Open
Add skip-raw-tensors property to gvaclassify and related components#780
Conversation
msmiatac
requested review from
a team,
BaoHuiling,
OskarFiedot,
ZiningLi,
dmichalo,
jmotow,
marcin-wadolkowski,
mholowni,
nszczygl9,
oonyshch,
pbartosik,
qianlongding,
tbujewsk,
tjanczak,
walidbarakat,
yangjianfeng1208 and
yunowo
as code owners
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
oonyshch
reviewed
Apr 15, 2026
| return model_proc_output_info; | ||
| } | ||
|
|
||
| bool shouldSkipRawTensors() const { |
Contributor
There was a problem hiding this comment.
overall, clean and readable accessor. one small thought: since shouldSkipRawTensors() is in protected, only derived converter classes can call it , and that's the right scope. pls consider adding a brief comment like: Returns true if raw output tensors should not be attached to inference results
…fy.h Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…fy.c Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverter_facade.h Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverter_facade.cpp Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…ob_to_meta_converter.h Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverters/to_tensor/text.h Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverters/to_tensor/text.cpp Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverters/to_tensor/label.cpp Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverters/to_tensor/docTR_ocr.cpp Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
…nverters/to_tensor/blob_to_tensor_converter.h Co-authored-by: Lena Onyshchenko <olena.onyshchenko@intel.com>
brmarkus
reviewed
Apr 16, 2026
| scheduling-policy : Scheduling policy across streams sharing same model instance: throughput (select first incoming frame), latency (select frames with earliest presentation time out of the streams sharing same model-instance-id; recommended batch-size less than or equal to the number of streams) | ||
| flags: readable, writable | ||
| String. Default: "throughput" | ||
| skip-raw-tensors : Skip attaching raw output tensors to metadata for gvaclassify post-processing. When false, converters may attach both interpreted results and raw tensor payloads. When true, only interpreted metadata is attached. |
There was a problem hiding this comment.
Can you add a note (here or in a README) about the purpose of "raw tensors", use-cases of "raw tensors", please? Or add a link to where "raw tensors" are already described, please?
Contributor
Author
There was a problem hiding this comment.
Good point! I'll add more information on "raw tensors" purpose and use cases.
tbujewsk
reviewed
Apr 21, 2026
| return model_proc_output_info; | ||
| } | ||
|
|
||
| bool shouldSkipRawTensors() const { |
Contributor
There was a problem hiding this comment.
- Can we use a common 'get' naming as it is done for other accessors/getters methods ?
getSkipRawTensors or just skipRawTensors , i.e. without 'should' - Add short comment as @oonyshch pointed out
tbujewsk
approved these changes
Apr 22, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
skip-raw-tensorsto control the attachment of raw output tensors in gvaclassify.