https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #41 from caulier.gil...@gmail.com ---
Look also this comment :
https://bugs.kde.org/show_bug.cgi?id=495014#c3
Typically, to be able to use opencl with opencv in digiKam, Mesa package need
to be installed.
Gilles Caulier
--
You are receiv
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #40 from Maik Qualmann ---
There is a project to provide CUDA on non-Nvidia GPUs.
https://github.com/vosen/ZLUDA
Maik
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #39 from Michael Miller ---
(In reply to Jonathan from comment #38)
> I only have a AMD CPU so CUDA is useless to me.
Hi Jonanathan,
That's ok. AMD can use OpenCL which will still allow for GPU offloading and
speedup. Follow these steps
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #38 from Jonathan ---
I only have a AMD CPU so CUDA is useless to me.
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #37 from Marshalleq ---
Cool, yeah there is a 4090 in the linux machine.
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #36 from Michael Miller ---
I'm using an M1 MacBook Pro, so we have that covered. Linux would be good,
especially if it has an NVidia CUDA capable GPU.
It's really whatever you want. The code is all the same for each platform.
Cheers,
M
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #35 from Marshalleq ---
(In reply to Michael Miller from comment #33)
> (In reply to atoms from comment #32)
>
> > That sounds really good. I have a huge collection, do you want me to help
> > you test / build anything?
>
> Hi Atoms,
> Ye
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #34 from Michael Miller ---
Hi Jonathan,
There is a bug in the code I just discovered. Face detection is ok. Face
recognition is not working right now. I'll let you know as soon as I fix the
bug.
Cheers,
Mike
--
You are receiving this
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #33 from Michael Miller ---
(In reply to atoms from comment #32)
> That sounds really good. I have a huge collection, do you want me to help
> you test / build anything?
Hi Atoms,
Yes! Tuning the models isn't an exact science. While the
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #32 from at...@electropositive.net ---
(In reply to Michael Miller from comment #28)
> Hi Jonathan,
> Yes, many, many things have changed. First, we've introduced 2 new models
> in 8.5.0. YuNet is now the preferred face detection model. It
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #27 from at...@electropositive.net ---
Has something specifically changed to make face detection / matching work
properly now? Because if there is nothing specific that can be pointed to, I
don't see how downloading new versions is going to
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #29 from Jonathan ---
I am currently in the process of a rescan, but due to quantity it is likely
that it will take another 16 hours.
Then I will do another training purge
then I will do another round of face recognition
I have a build date
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #31 from Michael Miller ---
Also, to speed things up, try using "Extra Large" as the face size settings.
"Large" is good, too. "Large" will be the default starting tomorrow.
Cheers,
Mike
--
You are receiving this mail because:
You are w
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #30 from Michael Miller ---
Hi Jonathan,
Please download a new build. I made some updates to the models yesterday.
Cheers,
Mike
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #28 from Michael Miller ---
Hi Jonathan,
Yes, many, many things have changed. First, we've introduced 2 new models in
8.5.0. YuNet is now the preferred face detection model. It is much faster
than YOLO and SSD. Second, we have a new face
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #26 from Michael Miller ---
Hi Jonathan,
When was the last time you downloaded digiKam? There was an issue in a build
from last week. The issue was even if you selected SFace in the settings, it
would still use OpenFace. Please download t
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #25 from Jonathan ---
The process is running to clear the training data ...please stand by
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #24 from Michael Miller ---
Hi Jonathan,
Let's start from the beginning.
You should be using YuNet to find the faces, 65% accuracy, and medium or large
face size.
After the faces are found, you should be using SFace to recognize (match) th
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #23 from Jonathan ---
Even set to 100% matching for face recognition it couldn't even match the faces
correctly. There are so many not even close matches it is funny.
--
You are receiving this mail because:
You are watching all bug change
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #22 from Jonathan ---
At the current settings the number of wrong faces to face matches is too high.
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #21 from Jonathan ---
I did the clear faces of unconfirmed, and I am scanning at the reccommed
settings. The scan has been running over night, and is now at 37% after more
that 8 hours of running.
--
You are receiving this mail because:
Y
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #20 from Jonathan ---
Another thing that is a problem is I will be clicking the check mark to
indicate that the name is correct, and suddenly without warning the whole
display will scroll up or down any where to 5-100 rows. This is complete
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #19 from at...@electropositive.net ---
(In reply to Michael Miller from comment #18)
> Hi Jonathan,
> First, please make sure you have the latest build from yesterday.
>
> Try these settings:
> Detection accuracy: 60%
> Model: YuNet
> Face
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #18 from Michael Miller ---
Hi Jonathan,
First, please make sure you have the latest build from yesterday.
Try these settings:
Detection accuracy: 60%
Model: YuNet
Face Size: Large
Recognition Accuracy: 60%
Model: SFace
Uncheck Work on al
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #17 from Jonathan ---
My face recognition is at 70
OpenFace
YuNet
Medium
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #16 from Michael Miller ---
Hi Jonathan,
Can you please tell us what settings you’re using? Which face detection model,
detection accuracy %, face size setting, face recognition model, and face
recognition accuracy %?
Cheers,
Mike
--
You
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #15 from Jonathan ---
I just got a hold of digikam 8.5 october 8th build.
I cleared the existing matches and it rescan, and it still isn't good.
My nephew has 20,000+ unconfirmed faces which don't match in the slightest.
I turned the accura
https://bugs.kde.org/show_bug.cgi?id=444160
Michael Miller changed:
What|Removed |Added
Assignee|digikam-bugs-n...@kde.org |michael_mil...@msn.com
--
You are receiving t
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #14 from Michael Miller ---
Thanks Gilles,
Yes, the accuracy rate of the new system in 8.5.0 is at least an order of
magnitude better than before.
Jonathan, the new face detection system (YuNet) is up to 30 times faster than
YOLO. The new
https://bugs.kde.org/show_bug.cgi?id=444160
caulier.gil...@gmail.com changed:
What|Removed |Added
CC||michael_mil...@msn.com
--- Comment #1
https://bugs.kde.org/show_bug.cgi?id=444160
Chris D changed:
What|Removed |Added
CC||sendchrissomej...@gmail.com
--- Comment #12 from Chri
https://bugs.kde.org/show_bug.cgi?id=444160
chim...@thespicers.net changed:
What|Removed |Added
Status|REPORTED|CONFIRMED
Ever confirmed|0
https://bugs.kde.org/show_bug.cgi?id=444160
chim...@thespicers.net changed:
What|Removed |Added
CC||chim...@thespicers.net
--
You are rec
https://bugs.kde.org/show_bug.cgi?id=444160
at...@electropositive.net changed:
What|Removed |Added
CC||at...@electropositive.net
--- Commen
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #9 from Hans Lauter ---
Created attachment 162319
--> https://bugs.kde.org/attachment.cgi?id=162319&action=edit
Wrong image recognition
An example: If I go on the suggestions for myself as a person in digikam.
Around 50-100 different peop
https://bugs.kde.org/show_bug.cgi?id=444160
Hans Lauter changed:
What|Removed |Added
CC||lavaw...@getnada.com
--- Comment #8 from Hans Lau
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #7 from caulier.gil...@gmail.com ---
@Jonathan,
This problem still reproducible with the new digiKam 8.2.0 pre-release Windows
installer available at usual place:
https://files.kde.org/digikam/
This new bundle is based on last Qt framewor
https://bugs.kde.org/show_bug.cgi?id=444160
caulier.gil...@gmail.com changed:
What|Removed |Added
CC||caulier.gil...@gmail.com
--- Comment
https://bugs.kde.org/show_bug.cgi?id=444160
José Oliver-Didier changed:
What|Removed |Added
CC||jose_oli...@hotmail.com
--
You are receiv
https://bugs.kde.org/show_bug.cgi?id=444160
Andrei changed:
What|Removed |Added
CC||avmaksi...@yandex.ru
--
You are receiving this mail b
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #5 from Maik Qualmann ---
Git commit 5258bccf8eca4ae28ae5075438c1a85bf895d4c5 by Maik Qualmann.
Committed on 02/06/2022 at 17:03.
Pushed by mqualmann into branch 'qt5-maintenance'.
fix wrong accuracy value in face recognition from maintenan
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #4 from dajomu ---
Are there any progress on this issue and especially what is mentioned in this
comment "Even though they may not match a known person they should be auto
categorized into groups of different unknown faces." Grouping unknown
https://bugs.kde.org/show_bug.cgi?id=444160
jan.waldh...@gmx.de changed:
What|Removed |Added
CC||jan.waldh...@gmx.de
--
You are receiving
https://bugs.kde.org/show_bug.cgi?id=444160
dajomu changed:
What|Removed |Added
CC||dajo...@gmail.com
--- Comment #3 from dajomu ---
I ag
https://bugs.kde.org/show_bug.cgi?id=444160
--- Comment #2 from Jonathan ---
Obviously it varies some have 100+ faces, and some only have a few samples.
However, I still have 20,000+ unmatched faces. Even though they may not match
a known person they should be auto categorized into groups of di
https://bugs.kde.org/show_bug.cgi?id=444160
Maik Qualmann changed:
What|Removed |Added
CC||metzping...@gmail.com
--- Comment #1 from Maik
46 matches
Mail list logo
