Skip to content

Improve face_recognition.md#30

Open
thomas-mc-work wants to merge 2 commits into
darktable-org:masterfrom
thomas-mc-work:patch-1
Open

Improve face_recognition.md#30
thomas-mc-work wants to merge 2 commits into
darktable-org:masterfrom
thomas-mc-work:patch-1

Conversation

@thomas-mc-work

Copy link
Copy Markdown

Improved the whole document.

Improved the whole document.
@DaemonLife

Copy link
Copy Markdown
Contributor

Very good change. Why was the request not accepted?

@thomas-mc-work

Copy link
Copy Markdown
Author

Thank you! I have no idea.

@wpferguson

Copy link
Copy Markdown
Member

Why was the request not accepted?

Yet


Because there is one of me and that one was

  • Fixing lots of bugs so 5.4.1 could get released
  • Packaging 5.4.1 for windows
  • Fixing more darktable bugs
  • Fixing lua bugs
  • Reviewing every issue/PR that is raised in darktable
  • Reviewing every issue/PR that is raised in the Lua scripts
  • Reviewing every issue/PR that is raised in the Lua docs
  • Helping establish guidelines for AI in darktable
  • Trying to fix the luadocs update process which is currently broken so no updates can be published.
  • Spending more time than I should on pixls.us answering questions and offering solutions
  • Adding lua scripts requested by users
  • and the one thing I wanted to get done for 5.6, bundle the lua-scripts with the darktable release.

And on top of that I have a real life with a longer list of issues than what's above


So, in short I saw this when it was submitted, didn't get to it, and forgot about it. Unfortunately we don't have a bot to remind every 60 days that there is something waiting.

@anoderay anoderay left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Some editorial notes

1. Install the face recognition solution https://github.com/ageitgey/face_recognition: `pipx install face-recognition`
2. Prepare your known faces in the following fashion:

You need a directory which holds the photos of all known faces. The file names are the tag names which will be used. You can add a number suffix to provide multiple photos of the same persone to improve the result. The number will be removed from the tag.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

typo "persone"

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Also maybe "number will be removed from the tag" = "number will not appear in the applied tag"

## Technical process

1. Selected images are exported into a temporary location with a lowered resolution
2. The external tool is invoced with the photo and the path to the face folder as parameters

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

invoced = invoked


1. Selected images are exported into a temporary location with a lowered resolution
2. The external tool is invoced with the photo and the path to the face folder as parameters
3. The result is parsed an dapplied as tags

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

missing space in "dapplied"

@wpferguson

Copy link
Copy Markdown
Member

@thomas-mc-work All of the script pages follow the same format, with the same headings. That way anyone using them can find what they want quickly knowing where the information will be based on on other script pages.

I'm kind of flexible about what you put under the headings. If you want to use subheadings under the headings that's fine.

Under Additional Software Required the content should be face_recognition and where to get it. If you want to add the steps for preparation there, that would work fine too.

## Usage

* start this script from script manager.
* start the recognition from the corresponding module ("face recognition") on the right side in the library view

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

you probably need to select some images before you try running the script

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.

4 participants