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

Unable to convert to frozen graph or checkpoint #64

Open
venkat-kittu opened this issue Oct 8, 2021 · 0 comments
Open

Unable to convert to frozen graph or checkpoint #64

venkat-kittu opened this issue Oct 8, 2021 · 0 comments

Comments

@venkat-kittu
Copy link

venkat-kittu commented Oct 8, 2021

I am trying to convert the densenet161 model to frozen graph(pb) or checkpoint, but after loading the model and while saving the checkpoint file I am getting the below error.
Thanks in advance

tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value batch_normalization_1/beta
[[node save/SaveV2 (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]

Below is the code for your reference

import densenet
import tensorflow as tf
model = densenet.DenseNetImageNet161(input_shape=(224,224,3))
saver = tf.train.Saver()
sess = tf.keras.backend.get_session()
save_path = saver.save(sess, "./checkpoint/model")

getting issue in the last line of code.

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

1 participant