CVS-176847 Reshape Input to apply to OVIR models as well #864
Conversation
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
n1harika
requested review from
RyanMetcalfeInt8,
ankitm3k and
jatinwadhwa921
n1harika
force-pushed
the
niharika/reshape_ovir
branch
from
e902bb9 to
1406fe4
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
To prevent recompilation of epctx models, a check was introduced to prevent the provider option 'reshape_input' from being used with epctx graphs. However, this also prevents OVIR models from compiling with the reshape input.
This PR modifies the check on epctx graphs to allow reshape for OVIR models and also adds a method to reshape it within the ImportEPCtxOVIREncapsulation() function.
Test:
onnxruntime_perf_test -m times -r 1 -e openvino -v -C "ep.context_enable|1 ep.context_file_path|ov_encoder_30_40_ctx.onnx" -i "device_type|NPU reshape_input|input_features[30..40,80,3000]" "openvino_encoder_model.onnx"
This should fail if input data>40 is provided.
Also removed redundant validation and checks on the OVEP side, to let OV handle reshape validation completely.