-
Notifications
You must be signed in to change notification settings - Fork 647
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
Support of Detectron2 models #24
Comments
Hello @justlike-prog! I gave a look at the Detectron2 source code and I found an easy way to implement a workaround for optimizing it. In The problem was that the backbone gives as output a dictionary and we need to map it to a tuple for being consistent with the Nebullvm API. I suggest defining two "wrapper" classes (one for the non-optimized and one for the optimized model) and then using them for running the Let's define the classes as
Then you can simply run the following code
If you need dynamic input shapes you'd need to add a few more arguments to the |
For now Detectron2 models don't work out of the box because of the different input format.
It would be nice to have an example on how to fix that.
Thanks!
The text was updated successfully, but these errors were encountered: