search

slashtechno / wyzely-detect

Recognize faces/objects in a video stream (from a webcam or a security camera) and send notifications to your devices
GNU Affero General Public License v3.0
12 stars 1 forks source link

Added support for multiple video sources #11

Closed slashtechno closed 9 months ago

slashtechno commented 9 months ago

It should now be possible to use multiple sources. For this to be useful, better configuration (toml maybe) should be added. This PR also updates dependencies and should make GPU dependencies optional. However, it seems poetry install -E cuda --with gpu switches every run between GPU and CPU for torch. This might be a Poetry issue.

slashtechno commented 9 months ago

I just remembered that objects_and_peoples is the same for all sources. I'm going to merge the PR with this in mind and fix it when I add more detection and configuration parameters.

slashtechno commented 9 months ago

The Dockerfile should also be updated once the problem with torch versions being switched between is resolved.