Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add quality modes and management docs #8732

Merged
merged 32 commits into from
Dec 4, 2024
Merged

Add quality modes and management docs #8732

merged 32 commits into from
Dec 4, 2024

Conversation

zhiltsov-max
Copy link
Contributor

@zhiltsov-max zhiltsov-max commented Nov 21, 2024

Motivation and context

  • Added information about dataset quality assurance featured added recently
  • Refactored the Immediate Feedback page

How has this been tested?

Checklist

  • I submit my changes into the develop branch
  • I have created a changelog fragment
  • I have updated the documentation accordingly
  • I have added tests to cover my changes
  • I have linked related issues (see GitHub docs)
  • I have increased versions of npm packages if it is necessary
    (cvat-canvas,
    cvat-core,
    cvat-data and
    cvat-ui)

License

  • I submit my code changes under the same MIT License that covers the project.
    Feel free to contact the maintainers if that's a concern.

Summary by CodeRabbit

  • New Features
    • Introduced a new document on quality control features, detailing validation sets, job validation, and quality analytics.
    • Updated the "Automated QA" document with new features and clearer guidance on quality assurance processes.
  • Documentation
    • Enhanced clarity and consistency across multiple documents, including updates to punctuation and formatting.
    • Restructured content for better understanding of automated quality control and immediate feedback mechanisms.

@zhiltsov-max zhiltsov-max marked this pull request as draft November 21, 2024 16:17
Copy link
Contributor

coderabbitai bot commented Nov 21, 2024

Important

Review skipped

Auto incremental reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Walkthrough

The pull request includes several modifications across three documents related to quality feedback and control in the CVAT system. The "Immediate job feedback" document has been refined for clarity and consistency, while the "Automated QA, Review & Honeypots" document has been significantly restructured to enhance understanding of annotation quality evaluation. Additionally, a new document titled "quality-control.md" has been introduced, providing a comprehensive overview of quality control features, including validation sets and job validation processes.

Changes

File Path Change Summary
site/content/en/docs/enterprise/immediate-feedback.md Textual modifications for clarity and consistency; punctuation and formatting adjustments; updated requirements for feedback.
site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md Title change; restructuring of content; expanded sections on validation sets and quality estimation; new section on quality estimation basics.
site/content/en/docs/manual/basics/quality-control.md New document introduced; overview of quality control features; instructions for enabling quality control for tasks.

Poem

🐰 In the garden of feedback, we hop with delight,
Clarity blooms, and the processes feel right.
With quality control, our tasks shine anew,
Each frame a treasure, each job a breakthrough!
So let’s leap with joy, as we refine and improve,
In the world of CVAT, we’ve found our groove! 🌼✨


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@zhiltsov-max zhiltsov-max marked this pull request as ready for review November 26, 2024 12:59
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🧹 Outside diff range and nitpick comments (8)
site/content/en/docs/manual/basics/quality-control.md (5)

14-15: Add a comma for better readability.

-In this section we only highlight the key steps in quality estimation.
+In this section, we only highlight the key steps in quality estimation.
🧰 Tools
🪛 LanguageTool

[typographical] ~14-~14: It appears that a comma is missing.
Context: ...to-check-task-quality-metrics) In this section we only highlight the key steps in qual...

(DURING_THAT_TIME_COMMA)


34-35: Enhance the formatting of the limitation notice.

The limitation about Ground Truth mode should be more prominent. Consider using a warning or note admonition.

-> For already existing tasks only the Ground Truth validation mode is available. If you want
-> to use Honeypots for your task, you will need to recreate the task.
+> **Warning**
+> For already existing tasks, only the Ground Truth validation mode is available. If you want
+> to use Honeypots for your task, you will need to recreate the task.
🧰 Tools
🪛 LanguageTool

[uncategorized] ~34-~34: A comma might be missing here.
Context: ...y existing task > For already existing tasks only the Ground Truth validation mode i...

(AI_EN_LECTOR_MISSING_PUNCTUATION_COMMA)


54-54: Fix typo in configuration guidance.

-1. Set **Max validations per job** to above zero. 3 is a good staring number.
+1. Set **Max validations per job** to above zero. 3 is a good starting number.

70-72: Consider adding more details about quality metrics.

The instructions would be more helpful with examples of:

  • What metrics are available in the summaries
  • What to look for in detailed reports
  • Typical completion time for metrics computation

Would you like me to help draft additional content for this section?


84-84: Consider adding a troubleshooting section.

The documentation would benefit from a section addressing common issues and their solutions, such as:

  • What to do if validation fails
  • How to handle conflicts in annotations
  • Steps to take when quality metrics are below expectations

Would you like me to help draft a troubleshooting section?

site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md (3)

14-14: Fix grammar and style issues for better readability.

Several grammar and style issues need to be addressed:

  1. Replace "2d" with "2D" for proper capitalization
  2. Fix "this methods" to "this method"
  3. Add missing commas after introductory phrases
-that quality estimation only supports 2d tasks
+that quality estimation only supports 2D tasks

-Note that using this methods can
+Note that using this method can

-In this mode some of the task frames
+In this mode, some of the task frames

-For each frame you can
+For each frame, you can

Also applies to: 217-217, 190-190, 226-226, 287-287, 292-292

🧰 Tools
🪛 LanguageTool

[grammar] ~14-~14: Did you mean “2D”(= two-dimensional) or “2nd” (= second)?
Context: ...that quality estimation only supports > 2d tasks. It supports all the annotation t...

(THREE_D)


[grammar] ~14-~14: Did you mean “2D”(= two-dimensional) or “2nd” (= second)?
Context: ...upports all the annotation types except 2d cuboids. > Note that tracks are co...

(THREE_D)


183-186: Enhance the explanation of validation modes.

The distinction between Ground Truth and Honeypots modes could be clearer. Consider adding a brief comparison table or diagram at the beginning of this section to help users quickly understand the key differences before diving into the details.


383-385: Consider moving premium feature notice to a more prominent location.

The note about quality analytics being a premium feature is buried in the middle of the document. Consider moving this important information to the beginning of the document or adding a "Prerequisites" section that clearly outlines what features require premium access.

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Reviewing files that changed from the base of the PR and between 3d7e2c7 and 9998749.

⛔ Files ignored due to path filters (5)
  • site/content/en/images/honeypot09.jpg is excluded by !**/*.jpg
  • site/content/en/images/honeypot10.jpg is excluded by !**/*.jpg
  • site/content/en/images/honeypot11.jpg is excluded by !**/*.jpg
  • site/content/en/images/honeypot12.jpg is excluded by !**/*.jpg
  • site/content/en/images/immediate-feedback-settings-validations.jpg is excluded by !**/*.jpg
📒 Files selected for processing (3)
  • site/content/en/docs/enterprise/immediate-feedback.md (2 hunks)
  • site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md (4 hunks)
  • site/content/en/docs/manual/basics/quality-control.md (1 hunks)
✅ Files skipped from review due to trivial changes (1)
  • site/content/en/docs/enterprise/immediate-feedback.md
🧰 Additional context used
🪛 LanguageTool
site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md

[grammar] ~14-~14: Did you mean “2D”(= two-dimensional) or “2nd” (= second)?
Context: ...that quality estimation only supports > 2d tasks. It supports all the annotation t...

(THREE_D)


[grammar] ~14-~14: Did you mean “2D”(= two-dimensional) or “2nd” (= second)?
Context: ...upports all the annotation types except 2d cuboids. > Note that tracks are co...

(THREE_D)


[grammar] ~64-~64: The usual collocation for “independently” is “of”, not “from”. Did you mean “independently of”?
Context: ...ion set images are sampled randomly and independently from the full dataset. That is, for the qual...

(INDEPENDENTLY_FROM_OF)


[typographical] ~190-~190: It appears that a comma is missing.
Context: ... be managed. ### Ground Truth In this mode some of the task frames are selected in...

(DURING_THAT_TIME_COMMA)


[grammar] ~217-~217: The singular determiner ‘this’ may not agree with the plural noun ‘methods’. Did you mean “these”?
Context: ...e quality in such jobs. Note that using this methods can result in increased total s...

(THIS_NNS)


[grammar] ~217-~217: Use the singular noun “method” with the word ‘this’.
Context: ...lity in such jobs. Note that using this methods can result in increased total size of t...

(DT_JJ_NNS_MD)


[typographical] ~226-~226: It appears that a comma is missing.
Context: ...b, if possible. ### Honeypots In this mode some random frames of the task are sele...

(DURING_THAT_TIME_COMMA)


[style] ~229-~229: Consider replacing ‘only’ with a different word to let your writing stand out.
Context: ...lidation frames are used. This mode can only be used at task creation and cannot be ...

(ONLY_EXCLUSIVELY_STYLE)


[formatting] ~267-~267: Consider inserting a comma after an introductory phrase for better readability.
Context: ...xample: a video annotation with tracks. In this case there is only 1 option - the Ground Tru...

(IN_THAT_CASE_COMMA)


[style] ~270-~270: Consider an alternative for the often overused word ‘important’.
Context: ... dataset annotation, image order is not important. Here you can use both options. You can...

(NOT_IMPORTANT)


[style] ~274-~274: Specify a number, remove phrase, use “a few”, or use “some”
Context: ...validation (for instance, you have only a small number of validation frames) or you want to allow...

(SMALL_NUMBER_OF)


[typographical] ~287-~287: It appears that a comma is missing.
Context: ... and review the frame details. For each frame you can see the number of uses in the t...

(DURING_THAT_TIME_COMMA)


[typographical] ~292-~292: It appears that a comma is missing.
Context: ... #### Frame changes In both validation modes it's possible to exclude some of the va...

(DURING_THAT_TIME_COMMA)


[grammar] ~294-~294: Did you mean “if” or “is” (with a reflexive pronoun)?
Context: ... validation frames are "bad", extra, or it they have incorrect annotations, which ...

(CC_IT_PRP)


[grammar] ~331-~331: The word “backup” is a noun. The verb is spelled with a space.
Context: ... on the honeypot frames. If you want to backup annotations, > use a task backup or exp...

(NOUN_VERB_CONFUSION)


[uncategorized] ~396-~396: Did you mean “if”?
Context: ...ated immediately** after task updates. It you want request quality metrics update...

(IT_IF_PREMIUM)

site/content/en/docs/manual/basics/quality-control.md

[typographical] ~14-~14: It appears that a comma is missing.
Context: ...to-check-task-quality-metrics) In this section we only highlight the key steps in qual...

(DURING_THAT_TIME_COMMA)


[uncategorized] ~34-~34: A comma might be missing here.
Context: ...y existing task > For already existing tasks only the Ground Truth validation mode i...

(AI_EN_LECTOR_MISSING_PUNCTUATION_COMMA)

🔇 Additional comments (2)
site/content/en/docs/manual/basics/quality-control.md (1)

1-6: LGTM! Front matter is well-structured.

The metadata is properly formatted and includes all necessary fields for documentation organization.

site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md (1)

167-167: Verify API references and update instructions.

A few items need verification:

  1. The link to Job API create() should be verified to ensure it's current
  2. The refresh process for quality metrics could benefit from more detailed steps or screenshots

Also applies to: 396-398

✅ Verification successful

Let me gather more information about the API documentation to verify the links and content.


Documentation appears complete with proper references and visual aids

The verification shows that:

  1. The API reference link is consistently used in the documentation
  2. The quality metrics refresh process is well documented with:
    • Clear instructions for manual refresh
    • A screenshot showing the refresh button location
    • Visual guides for reviewing the metrics
    • Explanation of computation time and requirements
🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Verify API documentation links
rg -l "Job API create\(\)" 

Length of output: 101


Script:

#!/bin/bash
# Check for API documentation files and references
fd -e md -e rst -e yaml api_sdk
rg -l "api_sdk/sdk/reference/apis/jobs-api"

Length of output: 150


Script:

#!/bin/bash
# Look for quality metrics documentation
rg -A 5 "quality metrics" "site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md"

Length of output: 941


Script:

#!/bin/bash
# Check if there are any screenshots or image references in the auto-qa documentation
rg -i "!\[.*\]" "site/content/en/docs/manual/advanced/analytics-and-monitoring/auto-qa.md"

Length of output: 707

site/content/en/docs/manual/basics/quality-control.md Outdated Show resolved Hide resolved

Import, export, and delete options are available from the
job's menu.
## Validation modes
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess using tabs can enhance the appearance of the documentation
image

site/content/en/docs/manual/basics/quality-control.md Outdated Show resolved Hide resolved
Copy link
Contributor

@Marishka17 Marishka17 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Overall LGTM 👍

Copy link

sonarqubecloud bot commented Dec 4, 2024

@zhiltsov-max zhiltsov-max merged commit f098ee5 into develop Dec 4, 2024
16 checks passed
@zhiltsov-max zhiltsov-max deleted the zm/quality-docs branch December 4, 2024 15:18
@zhiltsov-max zhiltsov-max mentioned this pull request Dec 4, 2024
7 tasks
zhiltsov-max added a commit that referenced this pull request Dec 4, 2024
<!-- Raise an issue to propose your change
(https://github.com/cvat-ai/cvat/issues).
It helps to avoid duplication of efforts from multiple independent
contributors.
Discuss your ideas with maintainers to be sure that changes will be
approved and merged.
Read the [Contribution guide](https://docs.cvat.ai/docs/contributing/).
-->

<!-- Provide a general summary of your changes in the Title above -->

### Motivation and context
<!-- Why is this change required? What problem does it solve? If it
fixes an open
issue, please link to the issue here. Describe your changes in detail,
add
screenshots. -->

Fixes invalid extension of an image changed in
#8732

### How has this been tested?
<!-- Please describe in detail how you tested your changes.
Include details of your testing environment, and the tests you ran to
see how your change affects other areas of the code, etc. -->

### Checklist
<!-- Go over all the following points, and put an `x` in all the boxes
that apply.
If an item isn't applicable for some reason, then ~~explicitly
strikethrough~~ the whole
line. If you don't do that, GitHub will show incorrect progress for the
pull request.
If you're unsure about any of these, don't hesitate to ask. We're here
to help! -->
- [ ] I submit my changes into the `develop` branch
- [ ] I have created a changelog fragment <!-- see top comment in
CHANGELOG.md -->
- [ ] I have updated the documentation accordingly
- [ ] I have added tests to cover my changes
- [ ] I have linked related issues (see [GitHub docs](

https://help.github.com/en/github/managing-your-work-on-github/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword))
- [ ] I have increased versions of npm packages if it is necessary

([cvat-canvas](https://github.com/cvat-ai/cvat/tree/develop/cvat-canvas#versioning),

[cvat-core](https://github.com/cvat-ai/cvat/tree/develop/cvat-core#versioning),

[cvat-data](https://github.com/cvat-ai/cvat/tree/develop/cvat-data#versioning)
and

[cvat-ui](https://github.com/cvat-ai/cvat/tree/develop/cvat-ui#versioning))

### License

- [ ] I submit _my code changes_ under the same [MIT License](
https://github.com/cvat-ai/cvat/blob/develop/LICENSE) that covers the
project.
  Feel free to contact the maintainers if that's a concern.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants