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

How to load model save_model format from tensorflow 2.x in opencv2? Tensorflow Object Detection API #18005

Closed
LuisEdMB opened this issue Aug 1, 2020 · 2 comments
Labels
question (invalid tracker) ask questions and other "no action" items here: https://forum.opencv.org

Comments

@LuisEdMB
Copy link

LuisEdMB commented Aug 1, 2020

Hello, how could I load a trained model in Tensorflow Object Detection API, in opencv2 to use DNN?

The format of the exported model is: save_model.

Tensorflow version: 2.2.0

Thanks!

@dkurt
Copy link
Member

dkurt commented Aug 2, 2020

Please try to convert saved_model to a frozen graph first. Take a look at #16879 (comment) and #16582 (comment).

@LuisEdMB
Copy link
Author

LuisEdMB commented Aug 2, 2020

@dkurt Thanks, I followed the first link, but I get the following:

"Can't create layer "StatefulPartitionedCall" of type "StatefulPartitionedCall" in function 'getLayerInstance'"

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question (invalid tracker) ask questions and other "no action" items here: https://forum.opencv.org
Projects
None yet
Development

No branches or pull requests

3 participants