[fix] Prevent Out-of-Memory Errors #180
Open
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
The primary issue is the inefficiency of repeatedly loading a large model into memory for each new instance of the `MMDetection` class. This process occurred every time an image required labeling, which led to rapidly exhausting available memory resources. Solution: The solution introduced a class-level attribute within the `MMDetection` class to store and share a single model instance across all instances of the class, ensuring the model loads only once. This approach dramatically reduced memory consumption and prevented out-of-memory errors by eliminating redundant model loading and leveraging model instance reuse.
JimmyMa99
approved these changes
Aug 21, 2024
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Outdated suggestions cannot be applied.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.
The primary issue is the inefficiency of repeatedly loading a large model into memory for each new instance of the
MMDetectionclass. This process occurred every time an image required labeling, which led to rapidly exhausting available memory resources.Solution:
The solution introduced a class-level attribute within the
MMDetectionclass to store and share a single model instance across all instances of the class, ensuring the model loads only once. This approach dramatically reduced memory consumption and prevented out-of-memory errors by eliminating redundant model loading and leveraging model instance reuse.