Closed dbuezas closed 8 years ago
Update: I generated the model.js from the original images and annotations and the result is also bad. Is there any trick I could try?
Hi, sorry for not replying to this sooner. I'm very busy finishing my master thesis, and also looking after a newborn, so don't have much time to follow up issues. Did you figure this out? As I understand you're trying to add more points to the model than the default 71.
Hi Audun, thanks for your message and I wish you luck with your master thesis.
Yes that's right, that is what I was trying to do. I also tried just to generate the model with the provided training data and somehow the results were also bad.
I am not working in this company anymore but I think they still want to get it going, feel free to contact them, it might be a good freelancing opportunity, I added the contact person as cc.
Best regards, David
David Buezas
On Wed, Jun 24, 2015 at 9:46 PM, Audun Mathias Øygard < notifications@github.com> wrote:
Hi, sorry for not replying to this sooner. I'm very busy finishing my master thesis, and also looking after a newborn, so don't have much time to follow up issues. Did you figure this out? As I understand you're trying to add more points to the model than the default 71.
— Reply to this email directly or view it on GitHub https://github.com/auduno/clmtools/issues/1#issuecomment-114991026.
I added some new points to the face training images and configured the tool to take them into account. I get the following Wargning:
And the precision of the tracker is horrible now.
Any tips? I started with the provided anotations.csv and adapted the model_viewer and pdm_builder to account for the new points.