Fix model type for classification #773
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
robiscoding
requested review from
PawelPeczek-Roboflow,
grzegorz-roboflow,
yeldarby,
probicheaux and
hansent
as code owners
PawelPeczek-Roboflow
requested changes
Nov 5, 2024
inference/core/cache/serializers.py
Outdated
| ] | ||
| predictions = [] | ||
| for pred in response.predictions: | ||
| if type(pred) == str: |
There was a problem hiding this comment.
please use isinstance(pred, str)
There was a problem hiding this comment.
if the clause is supposed to handle multi-label cls - then this is wrong approach whatsoever - please refer to response schemas
inference/core/cache/serializers.py
Outdated
| for pred in response.predictions: | ||
| if type(pred) == str: | ||
| predictions.append( | ||
| {"class": pred, "confidence": request.confidence} |
There was a problem hiding this comment.
this is not that clear for me - why to put a request confidence into predicted class name? That's the model which dictates confidence of prediction, request do only have threshold
There was a problem hiding this comment.
That was mistake, good catch
| ) | ||
|
|
||
|
|
||
| class TestSerializersClassification(unittest.TestCase): |
There was a problem hiding this comment.
we do not use unittest, but pytest - please adjust to the standard tool in repo
PawelPeczek-Roboflow
approved these changes
Nov 7, 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Outdated suggestions cannot be applied.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.
Description
model_typewhich is causing downstream issues in Model Monitoring (missing label/misreporting)Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Any specific deployment considerations
For example, documentation changes, usability, usage/costs, secrets, etc.
Docs