tensorflow / tensorflow/privacy

Does not work with eager mode

Open
#87 2 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
477
Avg merge
22h 12m
Merged PRs (30d)
1

Description

To reproduce:

  1. Go to tutorials/Classification_Privacy.ipynb
  2. Run the following
tf.compat.v1.enable_eager_execution()
assert tf.executing_eagerly()
  1. Run the notebook. Accuracy does not increase with training, stays at 0.1. If I remove the above two lines and rerun, accuracy increases as expected.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with tutorials/Classification_Privacy.ipynb and reproduce the reported behavior after enabling eager execution. Compare the notebook's training results with and without those two lines, then trace the affected training path. Done means the notebook's accuracy increases during training while eager execution remains enabled.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, python, tensorflow
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.