because of the model or something else? I just can't find the person.
There is no problem with the smart search, but the face recognition function has not responded
13 Replies
:wave: Hey @hjq,
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. :blue_square: read applicable release notes.
3. :blue_square: reviewed the FAQs for known issues.
4. :blue_square: reviewed Github for known issues.
5. :blue_square: tried accessing Immich via local ip (without a custom reverse proxy).
6. :blue_square: uploaded the relevant information (see below).
7. :blue_square: 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.what model are you using?
any error from the logs?
facial-recognition\buffalo_l
When I start the face detection task, Docker does not report any error logs
[05/22/25 10:47:37] INFO Loading detection model 'buffalo_l' to memory
[05/22/25 10:47:37] INFO Setting execution providers to
['CPUExecutionProvider'], in descending order of
preference
[05/22/25 10:47:37] INFO Loading recognition model 'buffalo_l' to memory
[05/22/25 10:47:37] INFO Setting execution providers to
['CPUExecutionProvider'], in descending order of
preference
immich-server
[Nest] 7 - 05/22/2025, 10:47:39 AM LOG [Microservices:PersonService] Detected 1 new faces in asset e422c57b-84d6-47c5-a313-ec2a7d8eedb9 But the character interface shows that no character is detected
[05/22/25 10:47:37] INFO Setting execution providers to
['CPUExecutionProvider'], in descending order of
preference
[05/22/25 10:47:37] INFO Loading recognition model 'buffalo_l' to memory
[05/22/25 10:47:37] INFO Setting execution providers to
['CPUExecutionProvider'], in descending order of
preference
immich-server
[Nest] 7 - 05/22/2025, 10:47:39 AM LOG [Microservices:PersonService] Detected 1 new faces in asset e422c57b-84d6-47c5-a313-ec2a7d8eedb9 But the character interface shows that no character is detected
what is your machine learning settings looks like?
it is by default needs three similar faces to create a new person
but face detection shouldn’t be like this
You mean face recognition requires more than three face photos?
it needs three similar faces to create a person
how many photos of the same person did you upload?
I uploaded more than 3 photos as you said and it worked. Face detection does not require the number of faces, it only needs faces to detect
Face detection does not require the number of faces, it only needs faces to detectyes it works exactly how you describe how ever, face recognition is different as you see from the log above face is indeed detected if you want to reduce the threshold, you can change that in Administration page > Settings > Machine learning > Facial recognition
change this to one
then you will have many faces, including strangers
Currently, immich only supports intelligent search and face recognition. Other models such as scene classification can be developed by yourself, right?
First of all, thank you for your prompt answer. I would also like to know how to display the pictures in thumbnails in chronological order or scenes.
chronological orderShould be possible using the timeline
Other models such as scene classification can be developed by yourself, right?Maybe, we haven't thought much about this. You can search for scene using smart search for sure