Update tutorials for keras 3 #120
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- tensorflow.keras -> keras - K.set_value(var, val) -> var.assign(val) - model.compile() must give list for metrics arg - variable.value() -> variable.numpy()
Tutorial 3 was crashing without having a unitary test crashing because we do not test clone method with given back_bounds
0 * C[:,0] was giving a sparse tensor (why?) which leads to an error. Using zeros_like() instead solves the issue (stay a non-sparse tensor)
This is the new minimum version of python for decomon beacause of keras 3.0
Even though this is actually a Functional model, it does not use its get_config() method because it is checked inside it that the __init__ method has the same signature as a functional model. Thus we enforce the get_config() from Functional by converting the model to a mere keras functional model and then add the properties specific to decomon. We add a test for it.
We are depending on tensorboard support for keras 3. See tensorflow/tensorboard#6686
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
tensorflow.keras->kerasK.set_value(var, val)->var.assign(val)model.compile()must give list for metrics argvariable.value()->variable.numpy()clone()with backbounds already defined (and a test to check it outside tutorials). This is used by tutorial 3 about adversarial attack.