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

pretrained yolo models #1

Open
lgarithm opened this issue Apr 20, 2018 · 3 comments
Open

pretrained yolo models #1

lgarithm opened this issue Apr 20, 2018 · 3 comments

Comments

@lgarithm
Copy link
Member

lgarithm commented Apr 20, 2018

darknet officially released

which are stored in darknet internal format.

I've written a converter which could read tensors from them.
Is there any models implemented in TL,
such that if I convert yoloi.weight into yoloi.npz, it could be used by the TL model.

@zsdonghao
Copy link
Member

@lgarithm hi, I have a WIP private repo, a master student is working on it.

@lgarithm
Copy link
Member Author

lgarithm commented May 1, 2018

lgarithm/crystalnet@7b58065#diff-4a7fc93aea4010278c6d52b293f3857c
It can convert yolov2.weights into idx format (the format of MNIST)

@lgarithm
Copy link
Member Author

yolov2 in C++ is almost done, the only thing left is remove overlaping detection boxes, which is relatively easy.
how about the python one?

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

No branches or pull requests

2 participants