Aadyaa Maddi

Hi @tr0p1x, thanks for opening the issue. > From what I can see, in fact, the error comes from the way SKLearn sets the thresholds for computing the false positive...

Hi @chris-prenode, just to confirm when you say: > if it seems that the MIA can't be successful You are speaking about the attack accuracy?

Hi @SydSeyedi could you post the exact error message? It would be helpful to debug your issue.

Hi all, I think the issue is both the python version and the tensorflow version being used. We've used the following versions to test the library: 1. Python `3.6` 2....

Hi @chris-prenode I will try the experiment with your ResNet model and get back to you.

Hi all, we have released a new version of our tool which works with the newer versions of TensorFlow and PyTorch. Hopefully this should resolve the gradient issue reported here.

Hi @yangshaojie0123, you can attack linear/logistic regression models by using a single layer `Sequential` model ([example](https://www.tensorflow.org/tutorials/keras/regression#linear_regression) on tensorflow docs). You'll need to pass tensorflow models to the tool if I'm...

Hi @detaimee, you can try to reduce the batch sizes for training/testing datasets. I also found this [stackoverflow question ](https://stackoverflow.com/questions/42495930/tensorflow-oom-on-gpu)that has some other approaches you can try.

Hi @cakirogluozan @2016312357 could you let me know the environment you are running ML Privacy Meter in i.e. python version, tensorflow version, etc.

Hi, please use tensorflow 2.1.0 and python 3.6 as stated in the README. The dependabot pull requests automatically updated the dependencies, I will change the tensorflow version in the requirements.txt...