Fix issue with hanging inference process due to excessive debug logs #32
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
|
This fixed the issue on my Rubik Pi running QNN |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
When an EIM or any underlying components (libraries, external SDKs, etc.) are dumping excessive logs into stdout or stderr, the classification may hang unexpectedly. The issue doesn't exist when the runner is initialized with the debug option:
The solution seems to be to redirect the stdout/stderr to devnull if the debug option is not being used (currently they are attached to PIPE).
Also, this PR adds a timeout for the IPC communication with EIM , so the classification script will crash if there is no response from EIM within 5 seconds (can be set to longer in runner init.
Fixes edgeimpulse/edgeimpulse#13967