restoring checkpoint loads weights partially #61859
Labels
comp:keras
Keras related issues
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
TF 2.13
For issues related to Tensorflow 2.13
type:bug
Bug
Issue type
Bug
Have you reproduced the bug with TensorFlow Nightly?
No
Source
source
TensorFlow version
tf 2.13.0
Custom code
Yes
OS platform and distribution
No response
Mobile device
No response
Python version
No response
Bazel version
No response
GCC/compiler version
No response
CUDA/cuDNN version
No response
GPU model and memory
No response
Current behavior?
I am following this tfa seq2seq tutorial for building a seq2seq network with LSTMs. I trained my model and got great accuracy. I saved my model with
tf.train.Checkpoint
. Then, I tried to reload my model withcheckpoint.restore(tf.train.latest_checkpoint(checkpoint_dir))
.However, the model gets restored partially.
My encoder weights get restored, however the decoder does not.
How to resolve?
Standalone code to reproduce the issue
Relevant log output
The text was updated successfully, but these errors were encountered: