Fix TensorFlow GradientTape example returning None due to tensor not …#284
Open
Lenakeiz wants to merge 1 commit intofchollet:masterfrom
Open
Fix TensorFlow GradientTape example returning None due to tensor not …#284Lenakeiz wants to merge 1 commit intofchollet:masterfrom
Lenakeiz wants to merge 1 commit intofchollet:masterfrom
Conversation
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix incorrect TensorFlow GradientTape example in Chapter 2
The original example initializes
xusingtf.zeros(), which creates a Tensor that is not automatically watched byGradientTape. As a result, the gradient computation returnsNoneType.This PR add explicitly the scalar tensor to be watched so it can be tracked by te gradient. Alternatively the scalar tensor could have been initialised as
tf.Variable(0.0)which are automatically tracked.Tested with TensorFlow 2.x.