Update MyDense example to use self.add_weight() for proper variable tracking #2401
+12 −3
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
…racking Fix: Update custom layer example to use self.add_weight() Problem: The previous MyDense layer created weights with tf.Variable in __init__. These weights were not automatically registered, so layer.variables and layer.trainable_variables were empty. This breaks standard Keras functionality for training, saving, and inspection. Solution: Updated MyDense to use self.add_weight(), which properly registers the weights with the layer. Now they appear in .variables and are fully tracked by Keras.
PreviewPreview and run these notebook edits with Google Colab: Rendered notebook diffs available on ReviewNB.com.Format and styleUse the TensorFlow docs notebook tools to format for consistent source diffs and lint for style:$ python3 -m pip install -U --user git+https://github.com/tensorflow/docsIf commits are added to the pull request, synchronize your local branch: git pull origin patch-2 |
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 Outdated suggestions cannot be applied.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: Update custom layer example to use self.add_weight()
Problem:
The previous MyDense layer created weights with tf.Variable in init. These weights were not automatically registered, so layer.variables and layer.trainable_variables were empty. This breaks standard Keras functionality for training, saving, and inspection.
Solution:
Updated MyDense to use self.add_weight(), which properly registers the weights with the layer. Now they appear in .variables and are fully tracked by Keras.