[QNN EP] Improve QDQ model accuracy tests #16916
Merged
Conversation
This file contains 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
HectorSVC
reviewed
Jul 31, 2023
HectorSVC
reviewed
Aug 3, 2023
HectorSVC
reviewed
Aug 3, 2023
adrianlizarraga
added a commit
that referenced
this pull request
Aug 9, 2023
### Description Slightly increases the allowable error tolerance for ReduceProd tests on x64 Windows/Linux with the QNN CPU backend. ### Motivation and Context A recent [PR](#16916) updated the input range for ReduceProd tests, which uncovered an inaccuracy for ReduceProd on x64 Windows/Linux with the QNN CPU backend. This PR updates the allowable error tolerance and adds a TODO for investigation. This is needed to ensure the QNN_Nuget_Windows pipeline runs successfully.
jchen351
pushed a commit
that referenced
this pull request
Aug 12, 2023
### Description - Improves how unit tests measure the accuracy of QDQ models on QNN EP. - Adds tests for ops: Add, Mul, Abs<sup>1</sup>, And<sup>1</sup>, Or<sup>1</sup>, Ceil<sup>1</sup>, Cos<sup>1</sup> <sup>1</sup>: Not previously supported due to missing node unit handling. ### Motivation and Context The new approach for testing QDQ operator accuracy requires running 3 inferences: 1. float model on CPU EP (baseline) 2. qdq model on CPU EP 3. qdq model on QNN EP The units tests check that running the QDQ model on QNN EP (3) is at least as accurate (+- small tolerance) as running the QDQ model on CPU EP (2). We measure accuracy by comparing to the baseline (1). This is essentially what we care about: is qnn ep as accurate as cpu ep. If not, it is worth investigating as a potential bug.
jchen351
pushed a commit
that referenced
this pull request
Aug 12, 2023
### Description Slightly increases the allowable error tolerance for ReduceProd tests on x64 Windows/Linux with the QNN CPU backend. ### Motivation and Context A recent [PR](#16916) updated the input range for ReduceProd tests, which uncovered an inaccuracy for ReduceProd on x64 Windows/Linux with the QNN CPU backend. This PR updates the allowable error tolerance and adds a TODO for investigation. This is needed to ensure the QNN_Nuget_Windows pipeline runs successfully.
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
### Description - Improves how unit tests measure the accuracy of QDQ models on QNN EP. - Adds tests for ops: Add, Mul, Abs<sup>1</sup>, And<sup>1</sup>, Or<sup>1</sup>, Ceil<sup>1</sup>, Cos<sup>1</sup> <sup>1</sup>: Not previously supported due to missing node unit handling. ### Motivation and Context The new approach for testing QDQ operator accuracy requires running 3 inferences: 1. float model on CPU EP (baseline) 2. qdq model on CPU EP 3. qdq model on QNN EP The units tests check that running the QDQ model on QNN EP (3) is at least as accurate (+- small tolerance) as running the QDQ model on CPU EP (2). We measure accuracy by comparing to the baseline (1). This is essentially what we care about: is qnn ep as accurate as cpu ep. If not, it is worth investigating as a potential bug.
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
…soft#17078) ### Description Slightly increases the allowable error tolerance for ReduceProd tests on x64 Windows/Linux with the QNN CPU backend. ### Motivation and Context A recent [PR](microsoft#16916) updated the input range for ReduceProd tests, which uncovered an inaccuracy for ReduceProd on x64 Windows/Linux with the QNN CPU backend. This PR updates the allowable error tolerance and adds a TODO for investigation. This is needed to ensure the QNN_Nuget_Windows pipeline runs successfully.
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.
Description
1: Not previously supported due to missing node unit handling.
Motivation and Context
The new approach for testing QDQ operator accuracy requires running 3 inferences:
The units tests check that running the QDQ model on QNN EP (3) is at least as accurate (+- small tolerance) as running the QDQ model on CPU EP (2). We measure accuracy by comparing to the baseline (1).
This is essentially what we care about: is qnn ep as accurate as cpu ep. If not, it is worth investigating as a potential bug.