tensorflow / tensorflow/privacy
DPKeras<name>Optimizer fail when Sequential model has layer with kernel_regularizer=tf.keras.regularizers.l2(l2_ratio)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 477
- Avg merge
- 22h 12m
- Merged PRs (30d)
- 1
Description
Hi,
I encountered a problem when adding regularization to Keras models using the new DPKerasOptimizer's with TF2.4.0 with (Sparse)CategoricalCrossentropy. The error (see below) can be reproduced by adding kernel_regularizer=tf.keras.regularizers.l2(1e-8)to a layer in mnist_dpsgd_tutorial_keras.py.
macos 10.15
python 3.7
Thanks in advance,
Craig
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the failure in mnist_dpsgd_tutorial_keras.py by adding kernel_regularizer=tf.keras.regularizers.l2(1e-8) to a layer and using the DPKerasOptimizer with TF2.4.0 and SparseCategoricalCrossentropy. Review the attached sysout.txt alongside the tutorial behavior; done means the tutorial runs successfully with the regularized layer.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100