Reset face recognition now there are significantly more assets?
I've been using Immich for a couple of months now, finding and adding more photos as I go. Over this time I've gradually added ~250GB of photos and videos and have been manually merging and tagging faces where needed. I've recently found & imported another 160GB of photos and videos.
Now I have a much larger library (44,000 photos & 1,700 videos), would it be worth resetting the facial recognition and running it over the whole library afresh? My understanding is that it should do a better job with more assets. I'm not sure how well it learns as a library grows.
I'll create a backup first, of course, I'd just be interested to know if it's worth investing the time to restart afresh, or if Immich is good at handling a growing library and there isn't much to be gained from restarting.
Thanks!
2 Replies
:wave: Hey @Adzwoolly,
Thanks for reaching out to us. Please carefully read this message and follow the recommended actions. This will help us be more effective in our support effort and leave more time for building Immich :immich:.
References
- Container Logs:
docker compose logs docs
- Container Status: docker ps -a docs
- Reverse Proxy: https://immich.app/docs/administration/reverse-proxy
- Code Formatting https://support.discord.com/hc/en-us/articles/210298617-Markdown-Text-101-Chat-Formatting-Bold-Italic-Underline#h_01GY0DAKGXDEHE263BCAYEGFJA
Checklist
I have...
1. :blue_square: verified I'm on the latest release(note that mobile app releases may take some time).
2. :ballot_box_with_check: read applicable release notes.
3. :ballot_box_with_check: reviewed the FAQs for known issues.
4. :ballot_box_with_check: reviewed Github for known issues.
5. :ballot_box_with_check: tried accessing Immich via local ip (without a custom reverse proxy).
6. :ballot_box_with_check: uploaded the relevant information (see below).
7. :ballot_box_with_check: tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable
(an item can be marked as "complete" by reacting with the appropriate number)
Information
In order to be able to effectively help you, we need you to provide clear information to show what the problem is. The exact details needed vary per case, but here is a list of things to consider:
- Your docker-compose.yml and .env files.
- Logs from all the containers and their status (see above).
- All the troubleshooting steps you've tried so far.
- Any recent changes you've made to Immich or your system.
- Details about your system (both software/OS and hardware).
- Details about your storage (filesystems, type of disks, output of commands like fdisk -l and df -h).
- The version of the Immich server, mobile app, and other relevant pieces.
- Any other information that you think might be relevant.
Please paste files and logs with proper code formatting, and especially avoid blurry screenshots.
Without the right information we can't work out what the problem is. Help us help you ;)
If this ticket can be closed you can use the /close command, and re-open it later if needed.Another aspect is where the model has identified a face in a rock or a trouser leg and found lots of matches, both random objects and real peoples' faces. I go through and delete these every now and again but, it keeps adding to it. I wonder if a reset would reduce the likelihood of this happening as (to anthropomorphise) it might not be so desperate to group them together when there are other potential matches.
Re-reading the docs hoping to better learn how it works, I came across a bit I'd missed/forgotten last time I read it.
"If you didn't import your assets at once or if the server was able to process jobs faster than you could upload them, it's possible that the clustering was suboptimal. If you haven't put effort into the current results, it may be worth re-running facial recognition on all assets for the best starting point. If it's too late for that, you can also manually assign a selection of unassigned faces and queue Missing for Facial Recognition to help it learn and assign more faces automatically."
I've done this before as I add faces, though now I have a much larger number of photos to add, I'm trying:
1. Running with higher minimum recognised faces (well, the default of 3) to reduce my work
2. After I've assigned the big groups, reducing it back down to 2 then 1 to catch any odd faces it couldn't identify.
I don't want to miss photos where possible but, also don't want to add lots of tiny groups. Hopefully with this I can get the best of both.
It'd be cool to have two settings, one for clustering (minimum recognised faces) and one for minimum group size to show in app. If I could have stricter clusters but, still view outliers that didn't make it into a cluster.