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

mumble module clean up #10

Closed
wants to merge 6,857 commits into from

Conversation

hungrymonkey
Copy link
Collaborator

I clean up the module and added a positional call.

I would need to add my audiostreamplayer. I am only doing a pull request because I have to work on this direction.

…layer now

checks if the user is giving truth boxes that can't be detected because the
non-max suppression settings would prevent them from being output at the same
time.  If this happens then we print a warning message and set one of the
offending boxes to "ignore".
…_trainer.

Also added an operator<< for dnn_trainer that prints the parameters it's using.

These changes also break backwards compatibility with the previous
serialization format for dnn_trainer objects.
…ay. Also

renamed the objects and generally improved documentation.
… the

concat layer's backward() method.  It was assigning the gradient to previous
layers instead of adding the gradient, as required by the layer interface
specification.  This change also noticeably speeds up concat layers since only
one CUDA kernel launch now happens per concat operation, rather than one
kernel launch for each sample in a tensor.
hungrymonkey and others added 28 commits October 10, 2017 21:06
…cb67d43'

git-subtree-dir: thirdparty/dlib
git-subtree-mainline: e1d3c6c
git-subtree-split: c2a9dee
…the facial resource loader because i have to convert file access to istream
Created a simple facial signal handler
…l_file_ending

Change file ending for facial trained models to f68
@hungrymonkey
Copy link
Collaborator Author

wrong branch

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