-
-
Notifications
You must be signed in to change notification settings - Fork 32
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
Configurable model #127
Configurable model #127
Conversation
Also prepare to add a property to select detector engine.
Tye type array2d does not work with CNN detector.
dbe49a3
to
5380a07
Compare
Also add a directory hierarchy for different models.
5380a07
to
b77fb70
Compare
When multiple threads access an image object in dlib's type, it caused crash. This crash happened when CPU has high load and correlation tracker becomes super slow. Instead of having the image in dlib's type, store in the thread-safe type obs_source_frame and create dlib's type in each thread.
c829253
to
7e16091
Compare
I started to try training on my machine. I'm afraid it will take several weeks. |
1ed2c50
to
8b668f7
Compare
I have not successfully generate the face detection model data yet. |
Description
Rewrite flow to process imagesI won't make this in this PR but will do this someday later.How Has This Been Tested?
General checklist