Fix model download issue: Download both .xml and .bin files #3012
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Outdated suggestions cannot be applied.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.
Fix model download and execution issues for person detection and re-identification
What changed
This PR addresses an issue where the model downloader was only fetching the
.xml
(model architecture) file but not the corresponding.bin
(model weights) file for OpenVINO models. This mismatch caused runtime errors like:Why this was needed
Both the
.xml
and.bin
files are required for OpenVINO IR (Intermediate Representation) models to run inference. Without the weights file, the model can't load or perform any predictions. Users trying to run the person detection (person-detection-0202
) or person re-identification (person-reidentification-retail-0287
) pipelines were hitting this error.What models are impacted
These models are often used together for multi-step pipelines (e.g., detect a person, then re-identify them across frames or cameras).
What I did
.xml
and.bin
files for each model are downloaded and available at runtime.How to test
.xml
and.bin
files exist in the expected download directory.Before this fix:
Running inference would fail with missing weights error.
After this fix:
Both models load successfully and inference runs as expected.