Guillaume Jeanneret

Hi, I had the same problem while running the training code. It seems that there is a deadlock with NCCL 2.7.8 [(check here)](https://github.com/pytorch/pytorch/issues/47885). Try using `export NCCL_P2P_DISABLE=1` before using it,...

Hi, I am also interested to know when the training code will be released. Thanks!

Hello, We did not train any classifier. The classifier and the oracle, we trained them using the [DiVE's code](https://github.com/ServiceNow/beyond-trivial-explanations). We shared the weights for future work to compare more fairly...

Hi, There are two flags you need to take into account when generating the counterfactuals. * `--query_label` selects which binary *task* to choose (e.g. 31 is smile/non-smile, 39 for young/old,...

Exactly!

Hi, With this information, it is a little hard to understand what is happening. But I'll give it a try. 1) When you say you are using no attack, do...

From what you say, I suspect that you trained your model without any normalization. Please try using the model I provided as another sanity check ([Link](https://drive.google.com/file/d/1OqjWns4NSu6AiKkOnpUOjUHzA8sQlaOA/view?usp=sharing))

Closed due to inactivity

Hi @sidney1505, 1. Is the downloaded generator the one I used, available [here](https://drive.google.com/file/d/17iB1aL4xctDukov-OIDuKqZdQ9YB1ZQz/view?usp=sharing)? My generator is not the best available. I merely used it for the constrained denoising. In fact,...

We do NOT want them to flip when we apply the filtering process. Recall that the filtering adds some noise and denoise it with the DDPM. Note that the filtering...