spectre-defense

spectre-defense copied to clipboard

Provide alternative to Julia dependency

5

It should be possible to reimplement the Julia half of the project in Python. This would be useful since not many ML researchers are familiar with Julia.

jhayase

Hi, I was using your quantum filter code on GTSRB dataset, where number of inputs in each class could be really small (

vtu81

Evaluating using My Own Code

3

Hi! Thanks for the nice work. I want to use the three approaches used here for comparison in my own pipeline. What I do is that 1. Train a model...

hmdolatabadi

The normalization of the loss in `mini_train` is slightly off if the batch does not have size `batch_size`, which can be the case when `drop_last` is false.

jhayase