SebastianCa
SebastianCa
Hi, it seems like you are running the code in XLA mode (i.e., you use the `@tf.function(jit_compile=True)` decorator when calling the e2e model). Depending on the version of TF and...
The error is clearly related to XLA. The E2E model in the `gnn.py` uses XLA (see [gnn.py L684](https://github.com/NVlabs/gnn-decoder/blob/26630040926d68ab2e748eb88d7c732225220b32/gnn.py#L684)), can you please try to set `jit_compile=False`? If this does not help,...
Hi @yj-ai, which version of TF and Sionna are you using? Did you modify the notebook before running?
Hi @paulalmasan, Could you please provide a code snippet that reproduces the error?
Closing as related to Sionna 0.19. If still relevant for Sionna 1.1, please open a new issue.
Hi @guillaume-larue, Thank you for the PR! We’ll review it carefully and get back to you, but please note that it might take a few weeks due to vacation time.
Closing due to inactivity
Closing as support for TensorFlow >2.15 has been resolved with the release of Sionna v1.0. Keras is no longer a required dependency.
Closing due to inactivity
Closing as irrelevant for Sionna 1.0.