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

Only getting prototxt file when trying to convert custom trained model #12

Open
fiorano10 opened this issue May 20, 2019 · 4 comments
Open

Comments

@fiorano10
Copy link

I have a custom model trained on Yolov2 for 1 class, when I try converting it caffe I get the protoxt file but no caffemodel. The script finishes with no other outputs/errors. what could be wrong?

@ysh329
Copy link
Owner

ysh329 commented May 21, 2019

Maybe no warn/error mentioned, you can check the converted prototxt file using netscope or netron, whether match your darknet cfg defined.

@fiorano10
Copy link
Author

fiorano10 commented May 21, 2019

There are a bunch of errors in the generated protoxt after checking it on netscope. I used darknet_alexey to train a model to detect custom class. Here are the weights, config, and generated prototxt I can detect objects using the weights so the training went okay, can't figure what's wrong. Thoughts?

@shiva13425
Copy link

Hi @fiorano10
I too have the same problem.. Is there any solution ?

@fiorano10
Copy link
Author

@shiva13425 Couldn't fix it

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

3 participants