CNOCycle

I have implemented a TF2 version for PGD attack in my fork project. The issues should be fixed. https://github.com/CNOCycle/cleverhans/tree/feature/tf2.x

After carefully comparing different implementations, I thought that `_residual_block` is also not correct. The original paper summaries that `residual function` in Figure 5. For basic black, a `relu` layer is...

Hi. Thank for your reminder. After checking the code for imagenet evaluation, the model architecture I used was the ResNet architecture provided by Robustbench but the width was set to...

I think that the subset I used for the evaluation might be different than the standard set provided by RobustBench. Besides, the evaluation was conducted almost two years ago, the...

I greatly appreciate your assistance. Those commits appear satisfactory to me.

The same issue for me. I have tried the solution provided by https://github.com/daquexian/onnx-simplifier/issues/214#issuecomment-1203845966 and https://github.com/daquexian/onnx-simplifier/issues/214#issuecomment-1206374649. Unfortunately, those solutions did not work for me. In my opinion, `metadata has 'unknown'` are...

Hi, @dkurt, Thank you for your valuable feedback. After careful consideration, I have decided to split this PR into two separate ones. The first will focus on implementing shape checkers,...

Thank you for providing a clear explanation of the data layout issue. It's important to note that the failed tests I mentioned earlier are not new tests related to the...

Apologies for the delayed response. I encountered a link error while attempting to build the scalable RVV on Debug mode from the latest `4.x` branch. I'm unsure of the origin...

Hi @dkurt, Thank you for the valuable feedback. Concerning the code complexity issues, it's essential to note that the transpose operation in TF implementation also encompasses six cases to handle...