[Model Overview] Metrics Template support with OD-specific optional args #2002
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
Advitya17
changed the title
Codecov Report
@@ Coverage Diff @@
## main #2002 +/- ##
=======================================
Coverage 92.37% 92.38%
=======================================
Files 95 95
Lines 4880 4882 +2
=======================================
+ Hits 4508 4510 +2
Misses 372 372
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
Advitya17
requested review from
imatiach-msft,
tongyu-microsoft,
xuke444,
RubyZ10,
vinuthakaranth,
romanlutz,
hawestra,
gaugup and
kicha0
as code owners
Advitya17
changed the title
Advitya17
changed the title
3 tasks
…olbox into agemawat/od_template
Advitya17
commented
Mar 15, 2023
| @@ -31,6 +31,8 @@ export interface IDataset { | |||
| feature_metadata?: IFeatureMetaData; | |||
| images?: string[]; | |||
| index?: string[]; | |||
| object_detection_true_y?: number[][][]; | |||
There was a problem hiding this comment.
- @imatiach-msft where are these python args passed to the typescript interfaces? Wish to emulate something similar to
feature_metadata:
Also the changes may involve defining a new interface, parsing python list to that interface, and including that interface in unit tests so I propose doing that in the next PR to avoid overloading this one.
There was a problem hiding this comment.
Thanks for investigating this! My concern here is that when implementing the explainability logic, I was planning on relying on the indexes of the bounding boxes. Would that still be possible with a dictionary representation? What would be the keys of the dictionary?
1 similar comment
imatiach-msft
approved these changes
Mar 20, 2023
gaugup
pushed a commit
that referenced
this pull request
Mar 23, 2023
…rgs (#2002) * OD label support ckpt * Surfaced OD metrics * numLabels update * lint fixes * main fetch * line end changes * var fix * ts lint fix * lint autofixes
gaugup
added a commit
that referenced
this pull request
Mar 23, 2023
* Add validations for model predictions Signed-off-by: Gaurav Gupta <gaugup@microsoft.com> * Add test Signed-off-by: Gaurav Gupta <gaugup@microsoft.com> * Undo change Signed-off-by: Gaurav Gupta <gaugup@microsoft.com> * Update notebooks for categorical features to pass through FeatureMetadata (#2011) * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-census-classification-model-debugging.ipynb * Update responsibleaidashboard-census-classification-model-debugging.ipynb * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-diabetes-regression-model-debugging.ipynb * Update responsibleaidashboard-census-classification-model-debugging.ipynb * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-housing-classification-model-debugging.ipynb * Update responsibleaidashboard-housing-classification-model-debugging.ipynb * Update responsibleaidashboard-census-classification-model-debugging.ipynb * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-diabetes-regression-model-debugging.ipynb * Update responsibleaidashboard-housing-decision-making.ipynb * Update responsibleaidashboard-multiclass-dnn-model-debugging.ipynb * Update responsibleaidashboard-diabetes-decision-making.ipynb * Update responsibleaidashboard-diabetes-regression-model-debugging.ipynb * Update responsibleaidashboard-housing-classification-model-debugging.ipynb * Update responsibleaidashboard-housing-decision-making.ipynb * [Model Overview] Metrics Template support with OD-specific optional args (#2002) * OD label support ckpt * Surfaced OD metrics * numLabels update * lint fixes * main fetch * line end changes * var fix * ts lint fix * lint autofixes * Object Detection Model Overview Flask template (#2004) * flask endpoint infra template * docstring and lint fixes * lint fixes * lint fixes * lint autofixes * error statement fix * Model Overview: Object Detection Widgets for Aggregate Methods, Class selection, & IoU Threshold (#1997) * agg method & iou thresh widgets ckpt * class selection widget * widget option format fix * comment fixes * widget size & lint fixes * semiclon lint fix * od widget options refactor * lint complexity fixes * lint complexity fixes * comment fixes * refactor to reduce complexity * complexity refactor * lint fixes * autolint fixes * Address code review comments Signed-off-by: Gaurav Gupta <gaugup@microsoft.com> --------- Signed-off-by: Gaurav Gupta <gaugup@microsoft.com> Co-authored-by: tongy-msft <91754176+tongyu-microsoft@users.noreply.github.com> Co-authored-by: Advitya Gemawat <agemawat@ucsd.edu> Co-authored-by: Advitya Gemawat <agemawat@microsoft.com>
3 tasks
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
This PR defines enums and template functions for object detection support in the Model Overview section (and parts of Data Characteristics view).
This PR also adds in optional args (i.e.
object_detection_{true/predicted}_yto the dataset interfaces) to store the OD label representation:This PR explores an alternate direction to #1995 .
Checklist