tensorflow / tensorflow/privacy
Issues in Integrating Differential Privacy in Keras Custom Loss Function
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 477
- Avg merge
- 22h 12m
- Merged PRs (30d)
- 1
Description
How to return a vector loss in Keras Custom Loss function, So that I don't have a issue with the following error:
ValueError: Dimension size must be evenly divisible by 256 but is 1 for 'Reshape' (op: 'Reshape') with input shapes: [], [2] and with input tensors computed as partial shapes: input[1] = [256,?].
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 reported Keras custom loss error involving a vector loss and the reshape to dimension 256. Inspect how the loss output shape is passed into the differential privacy training path. Done means the custom loss integrates without the reported ValueError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- keras, python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100