Vishnu Asutosh Dasu
Results
2
issues of
Vishnu Asutosh Dasu
The `noise_multiplier` in the MNIST Keras tutorials is extremely low (0.1). This results in an epsilon of 66416.55 after 60 epochs of training. Looks like this is a typo introduced...
## Description Closes #230. ## Affected Dependencies N.A. ## How has this been tested? Python tests have passed successfully. ## Checklist - [x] I have followed the [Contribution Guidelines](https://github.com/OpenMined/.github/blob/master/CONTRIBUTING.md) and...