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

Fix det_prob_threshold in compreface detector test #185

Merged
merged 1 commit into from
May 23, 2022

Conversation

bigbangus
Copy link
Contributor

Changed det_prob_threshold from 0 to 0.8 when testing the compreface detector to address issue with compreface custom-builds.

@juan11perez
Copy link

I have very similar hardware (GTX 1050Ti, Ryzen 9 3900X w/64MB RAM) with unraid 6.9.2 and experienced exactly the same issue.

I have modified the double-take docker per above referred pull request and it now works with mobilenet-gpu.

Thank you

@wills106
Copy link

wills106 commented Jan 20, 2022

Just want to confirm this fix has resolved my problem as well. I am running single container compreface:0.6.1-arcface-r100-gpu on a GTX1650 running Unraid 6.10.0-rc2

@bigbangus
Copy link
Contributor Author

@jakowenko do you think it would be possible to roll this into the next release?

@steppel
Copy link

steppel commented Mar 24, 2022

Any update on that?

@steppel
Copy link

steppel commented Mar 28, 2022

Changed det_prob_threshold from 0 to 0.8 when testing the compreface detector to address issue with compreface custom-builds.

@bigbangus I did spin up a container with the change you suggest. I still have the same problem. You sure thats the reason?

192.168.1.xxx - - [28/Mar/2022:12:45:57 -0700] "POST /api/v1/recognition/recognize?face_plugins=undefined&det_prob_threshold=0.8 HTTP/1.1" 499 0 "-" "axios/0.24.0"

@bigbangus
Copy link
Contributor Author

Changed det_prob_threshold from 0 to 0.8 when testing the compreface detector to address issue with compreface custom-builds.

@bigbangus I did spin up a container with the change you suggest. I still have the same problem. You sure thats the reason?

192.168.1.xxx - - [28/Mar/2022:12:45:57 -0700] "POST /api/v1/recognition/recognize?face_plugins=undefined&det_prob_threshold=0.8 HTTP/1.1" 499 0 "-" "axios/0.24.0"

Are you sure this is the same issue. You can read in detail what the problem is here: exadel-inc/CompreFace#691

Are you sure you're having an issue with the lenna.jpg test on compreface gpu custom builds?

@juan11perez
Copy link

@jakowenko
Can you please consider this request for next release? the proposed solution resolves the problem and I noticed your latest version is unchanged.
Thank you

@bigbangus
Copy link
Contributor Author

So far it's been very stable with compreface gpu as long as I avoid the /config page, but yes would be great to have this change considered thank you!

@jakowenko jakowenko changed the base branch from master to beta May 23, 2022 04:18
@jakowenko jakowenko merged commit 439179a into jakowenko:beta May 23, 2022
jakowenko added a commit that referenced this pull request May 23, 2022
## [1.9.0-beta.2](v1.9.0-beta.1...v1.9.0-beta.2) (2022-05-23)

### Bug Fixes

* det_prob_threshold in compreface detector test ([#185](#185)) ([439179a](439179a))
@jakowenko
Copy link
Owner

🎉 This PR is included in version 1.9.0-beta.2 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀

jakowenko added a commit that referenced this pull request May 23, 2022
## [1.9.0](v1.8.0...v1.9.0) (2022-05-23)

### Features

* **api:** update frigate sub label ([ad40018](ad40018))

### Bug Fixes

* det_prob_threshold in compreface detector test ([#185](#185)) ([439179a](439179a))

### Build

* copy .eslintrc.js during build process ([a89db5c](a89db5c))
* **deps:** package updates ([f2936f6](f2936f6))
* semantic versioning for beta builds ([cc617c9](cc617c9))
@jakowenko
Copy link
Owner

🎉 This PR is included in version 1.9.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀

@jakowenko
Copy link
Owner

Sorry for the delay in this. This is implemented now in v1.9.0. Let me know if you run into any issues. The Docker image is building now and should be done in about an hour.

@juan11perez
Copy link

@jakowenko thank you for your prompt reply.
It's now working well with the single 'exadel/compreface:0.6.1-mobilenet-gpu' docker.

@bigbangus
Copy link
Contributor Author

@jakowenko thank you! #myfirstpr

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

5 participants