DATA-3462 - Refactor code for using in Cloud inference #4792
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
tahiyasalam
changed the title
viambot
added
the
safe to test
viambot
added
safe to test
bhaney
requested changes
Feb 28, 2025
services/vision/mlvision/detector.go
Outdated
Comment on lines
157
to
164
| func GetIndex(s []int, num int) int { | ||
| for i, v := range s { | ||
| if v == num { | ||
| return i | ||
| } | ||
| } | ||
| return -1 | ||
| } |
There was a problem hiding this comment.
This is repeated from the new ml/ml.go function GetIndex, would you remove this one and use that one from ml package?
viambot
added
safe to test
bhaney
approved these changes
Mar 5, 2025
viambot
added
safe to test
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Outdated suggestions cannot be applied.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.
Hi! This is another refactor that I had to put together in order to allow Cloud inference to have parity with the vision code. You'll notice that I changed the output response of the FormatDetection to be BoundingBoxes (with relative coordinates) that are then converted into Detections. This is to prevent information loss when switching from relative coordinates -> absolute coordinates -> relative coordinates in Cloud inference. Instead, we just return relative coordinates, which are used directly in Cloud inference, but then converted for the vision service.
I tested to make sure everything was running as intended using the EfficientDet-COCO TFLite module with stable RDK (top) and then with the new changes (bottom)
