Add BatchNorm layers to CNN in MNIST tutorial for improved training stability#4773
Merged
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Contributor
|
Thanks for the update |
…ning stability and performance. Update training and evaluation steps to switch model modes appropriately. Clarify documentation on the use of .eval() for inference.
cgarciae
approved these changes
Aug 3, 2025
Collaborator
|
@sanepunk looks good! You can fix pre-commit with: |
- Removed explicit `ipython3` specification from code cells for uniformity. - Improved formatting and readability of code snippets throughout the document.
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
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Integrates
nnx.BatchNorminto the CNN model used indocs_nnx/mnist_tutorial.ipynb. Enables batch-norm-aware behavior with.train()and.eval()modes to improve convergence and metrics visualization.Highlights
nnx.BatchNorm()after each convolutionmodel.train()so running statistics are updatedmodel.eval()in the evaluation loop for deterministic inferenceWhy?
BatchNorm stabilizes and accelerates training by normalizing activations between layers, leading to better gradient flow and faster convergence.
Testing
Ran the MNIST tutorial notebook end-to-end and confirmed:
Closes #