tensorflow / tensorflow/privacy
AttributeError: module 'tensorflow_privacy.privacy.analysis.compute_dp_sgd_privacy' has no attribute 'compute_dp_sgd_privacy'
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 477
- Avg merge
- 22h 12m
- Merged PRs (30d)
- 1
Description
Hi,
I am trying to measure the differential privacy guarantee by using the ".compute_dp_sgd_privacy". However, itt show the following error. I installed the package as well. But don't know why that is happen. Could anyone help to solve this problem.
AttributeError Traceback (most recent call last)
in <cell line: 1>()
----> 1 compute_dp_sgd_privacy.compute_dp_sgd_privacy(n=train_data.shape[0],
2 batch_size=batch_size,
3 noise_multiplier=noise_multiplier,
4 epochs=epochs,
5 delta=1e-5)
AttributeError: module 'tensorflow_privacy.privacy.analysis.compute_dp_sgd_privacy' has no attribute 'compute_dp_sgd_privacy'
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
Start by reproducing the traceback from the notebook call to tensorflow_privacy.privacy.analysis.compute_dp_sgd_privacy.compute_dp_sgd_privacy and inspect the installed module's available entry points. Done means the differential-privacy calculation can be invoked with the shown parameters without the AttributeError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning, security
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100